Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4083 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.4916. Min Act: -0.1700
Data Index: 6558531 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.4916. Min Act: -0.1700
Data Index: 7630498 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.4603. Min Act: -0.1700
Data Index: 3164700 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.4916. Min Act: -0.1700
Data Index: 396425 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.4603. Min Act: -0.1700
Data Index: 3164702 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.4291. Min Act: -0.1700
Data Index: 6558533 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.4603. Min Act: -0.1700
Data Index: 396427 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.3978. Min Act: -0.1700
Data Index: 7630500 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4916. Min Range: -5.4916
Max Act: 4.9916. Min Act: -0.1700
Data Index: 6410503 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.0228. Min Act: -0.1700
Data Index: 7298939 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.0228. Min Act: -0.1700
Data Index: 5155799 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.0541. Min Act: -0.1700
Data Index: 7367647 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4916. Min Range: -5.4916
Max Act: 5.0228. Min Act: -0.1700
Data Index: 6196397 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4916. Min Range: -5.4916
Max Act: 4.9291. Min Act: -0.1700
Data Index: 7080248 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4916. Min Range: -5.4916
Max Act: 4.8978. Min Act: -0.1700
Data Index: 5199449 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4916. Min Range: -5.4916
Max Act: 4.8666. Min Act: -0.1700
Data Index: 5328289 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4916. Min Range: -5.4916
Max Act: 4.8353. Min Act: -0.1700
Data Index: 8403570 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4916. Min Range: -5.4916
Max Act: 4.8041. Min Act: -0.1700
Data Index: 888030 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4916. Min Range: -5.4916
Max Act: 4.7416. Min Act: -0.1700
Data Index: 5629811 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4916. Min Range: -5.4916
Max Act: 4.7103. Min Act: -0.1700
Data Index: 8129517 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19