Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1919. Min Range: -9.1919
Max Act: 9.1919. Min Act: -0.1700
Data Index: 6598671 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1919. Min Range: -9.1919
Max Act: 9.0669. Min Act: -0.1700
Data Index: 3117675 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.9419. Min Act: -0.1700
Data Index: 3060278 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.8169. Min Act: -0.1700
Data Index: 988798 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.6919. Min Act: -0.1700
Data Index: 5248961 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.6919. Min Act: -0.1700
Data Index: 670979 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.6294. Min Act: -0.1700
Data Index: 5276690 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.6294. Min Act: -0.1700
Data Index: 2618195 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.5669. Min Act: -0.1700
Data Index: 2424118 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.5669. Min Act: -0.1700
Data Index: 30061 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.5044. Min Act: -0.1700
Data Index: 1377781 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.5044. Min Act: -0.1700
Data Index: 8801867 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.5044. Min Act: -0.1700
Data Index: 5945458 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.4419. Min Act: -0.1700
Data Index: 8231866 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.5044. Min Act: -0.1700
Data Index: 5802719 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.5044. Min Act: -0.1700
Data Index: 1407930 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.4419. Min Act: -0.1700
Data Index: 1168742 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.3794. Min Act: -0.1700
Data Index: 2678937 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.3794. Min Act: -0.1700
Data Index: 815322 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1919. Min Range: -9.1919
Max Act: 8.3794. Min Act: -0.1700
Data Index: 2819992 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19