Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1044 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.7667. Min Act: -0.1700
Data Index: 1417774 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.7667. Min Act: -0.1700
Data Index: 5334492 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.7042. Min Act: -0.1700
Data Index: 5167490 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.7042. Min Act: -0.1700
Data Index: 2939526 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.6417. Min Act: -0.1700
Data Index: 7566073 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.4542. Min Act: -0.1700
Data Index: 1706471 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.4542. Min Act: -0.1700
Data Index: 1066652 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.4542. Min Act: -0.1700
Data Index: 724768 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.3917. Min Act: -0.1700
Data Index: 6112885 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.3917. Min Act: -0.1700
Data Index: 1076087 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.3292. Min Act: -0.1700
Data Index: 6314762 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.3292. Min Act: -0.1700
Data Index: 3176292 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.2667. Min Act: -0.1700
Data Index: 8801471 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.2042. Min Act: -0.1700
Data Index: 7365463 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.2042. Min Act: -0.1700
Data Index: 6892550 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.2667. Min Act: -0.1700
Data Index: 4736682 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.2042. Min Act: -0.1700
Data Index: 7694632 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.2667. Min Act: -0.1700
Data Index: 6012796 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.1417. Min Act: -0.1700
Data Index: 3457099 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7667. Min Range: -11.7667
Max Act: 11.0792. Min Act: -0.1700
Data Index: 1812915 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19