Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3255 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.7667. Min Act: -0.1700
Data Index: 3798640 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.7042. Min Act: -0.1700
Data Index: 1117027 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.6104. Min Act: -0.1700
Data Index: 3798639 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.3917. Min Act: -0.1700
Data Index: 3798638 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.3292. Min Act: -0.1700
Data Index: 1117025 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.2667. Min Act: -0.1700
Data Index: 3798636 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.2354. Min Act: -0.1700
Data Index: 3088225 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.2042. Min Act: -0.1700
Data Index: 3798637 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.2354. Min Act: -0.1700
Data Index: 3798634 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.1104. Min Act: -0.1700
Data Index: 3798631 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.0479. Min Act: -0.1700
Data Index: 3088231 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.0479. Min Act: -0.1700
Data Index: 4381152 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.0792. Min Act: -0.1700
Data Index: 8573819 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7667. Min Range: -5.7667
Max Act: 5.0167. Min Act: -0.1700
Data Index: 3144641 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7667. Min Range: -5.7667
Max Act: 4.9854. Min Act: -0.1700
Data Index: 3687344 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7667. Min Range: -5.7667
Max Act: 4.9854. Min Act: -0.1700
Data Index: 240872 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7667. Min Range: -5.7667
Max Act: 4.9542. Min Act: -0.1700
Data Index: 5322519 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7667. Min Range: -5.7667
Max Act: 4.9229. Min Act: -0.1700
Data Index: 7975478 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7667. Min Range: -5.7667
Max Act: 4.9229. Min Act: -0.1700
Data Index: 6599635 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7667. Min Range: -5.7667
Max Act: 4.8917. Min Act: -0.1700
Data Index: 5003067 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19