Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6382 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.3790. Min Act: -0.1700
Data Index: 7861721 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.2228. Min Act: -0.1700
Data Index: 1770007 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.1915. Min Act: -0.1700
Data Index: 7888157 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.1290. Min Act: -0.1700
Data Index: 4109638 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.1290. Min Act: -0.1700
Data Index: 2231098 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.0978. Min Act: -0.1700
Data Index: 6168546 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.0978. Min Act: -0.1700
Data Index: 8481151 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.0353. Min Act: -0.1700
Data Index: 2818962 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.0665. Min Act: -0.1700
Data Index: 5680041 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.0040. Min Act: -0.1700
Data Index: 6277261 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3790. Min Range: -5.3790
Max Act: 5.0040. Min Act: -0.1700
Data Index: 6864302 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3790. Min Range: -5.3790
Max Act: 4.9728. Min Act: -0.1700
Data Index: 5803846 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3790. Min Range: -5.3790
Max Act: 4.9728. Min Act: -0.1700
Data Index: 526957 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3790. Min Range: -5.3790
Max Act: 4.9415. Min Act: -0.1700
Data Index: 7758942 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3790. Min Range: -5.3790
Max Act: 4.9103. Min Act: -0.1700
Data Index: 511966 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3790. Min Range: -5.3790
Max Act: 4.9103. Min Act: -0.1700
Data Index: 729688 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3790. Min Range: -5.3790
Max Act: 4.9103. Min Act: -0.1700
Data Index: 1405737 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3790. Min Range: -5.3790
Max Act: 4.9103. Min Act: -0.1700
Data Index: 4781642 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3790. Min Range: -5.3790
Max Act: 4.9103. Min Act: -0.1700
Data Index: 865635 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3790. Min Range: -5.3790
Max Act: 4.9103. Min Act: -0.1700
Data Index: 927451 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19