Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6358 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.9037. Min Act: -0.1700
Data Index: 3605300 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.8412. Min Act: -0.1700
Data Index: 3605310 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.8412. Min Act: -0.1700
Data Index: 2996049 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.7787. Min Act: -0.1700
Data Index: 7202243 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.7787. Min Act: -0.1700
Data Index: 2996037 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.7162. Min Act: -0.1700
Data Index: 1164814 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.7162. Min Act: -0.1700
Data Index: 1164818 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.7162. Min Act: -0.1700
Data Index: 4028720 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.7162. Min Act: -0.1700
Data Index: 2151094 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.6537. Min Act: -0.1700
Data Index: 3217836 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.6537. Min Act: -0.1700
Data Index: 4412578 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.5287. Min Act: -0.1700
Data Index: 7983523 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.5287. Min Act: -0.1700
Data Index: 424663 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.5287. Min Act: -0.1700
Data Index: 6632618 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.5287. Min Act: -0.1700
Data Index: 7983511 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.5287. Min Act: -0.1700
Data Index: 3759212 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.5287. Min Act: -0.1700
Data Index: 3718613 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.5287. Min Act: -0.1700
Data Index: 7219070 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.5287. Min Act: -0.1700
Data Index: 2032061 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9037. Min Range: -8.9037
Max Act: 8.5912. Min Act: -0.1700
Data Index: 3217840 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19