Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3793 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.4948. Min Act: -0.1700
Data Index: 2695721 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.3385. Min Act: -0.1700
Data Index: 415565 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.3385. Min Act: -0.1700
Data Index: 4570417 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.1823. Min Act: -0.1700
Data Index: 3079732 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.1510. Min Act: -0.1700
Data Index: 101140 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.1198. Min Act: -0.1700
Data Index: 2696402 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.1198. Min Act: -0.1700
Data Index: 2926100 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.0885. Min Act: -0.1700
Data Index: 8271337 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.0885. Min Act: -0.1700
Data Index: 1236360 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.0885. Min Act: -0.1700
Data Index: 7515702 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.1198. Min Act: -0.1700
Data Index: 597690 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.0572. Min Act: -0.1700
Data Index: 4976298 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.0260. Min Act: -0.1700
Data Index: 152245 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.0572. Min Act: -0.1700
Data Index: 7781085 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4948. Min Range: -4.4948
Max Act: 3.9947. Min Act: -0.1700
Data Index: 4678002 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.0260. Min Act: -0.1700
Data Index: 2607908 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4948. Min Range: -4.4948
Max Act: 3.9947. Min Act: -0.1700
Data Index: 734651 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4948. Min Range: -4.4948
Max Act: 3.9635. Min Act: -0.1700
Data Index: 7039094 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4948. Min Range: -4.4948
Max Act: 4.0260. Min Act: -0.1700
Data Index: 3226940 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4948. Min Range: -4.4948
Max Act: 3.9322. Min Act: -0.1700
Data Index: 2644541 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19