Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1053 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.6407. Min Act: -0.1700
Data Index: 1926167 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.6095. Min Act: -0.1700
Data Index: 4274637 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.6095. Min Act: -0.1700
Data Index: 1221853 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.6095. Min Act: -0.1700
Data Index: 3185741 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.6095. Min Act: -0.1700
Data Index: 6379177 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.5470. Min Act: -0.1700
Data Index: 2256218 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.5782. Min Act: -0.1700
Data Index: 3653423 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.5782. Min Act: -0.1700
Data Index: 6186778 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.5470. Min Act: -0.1700
Data Index: 5987774 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.5470. Min Act: -0.1700
Data Index: 8671720 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.5157. Min Act: -0.1700
Data Index: 418957 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.5157. Min Act: -0.1700
Data Index: 8132988 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.5157. Min Act: -0.1700
Data Index: 8554942 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.5157. Min Act: -0.1700
Data Index: 997071 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.4845. Min Act: -0.1700
Data Index: 5223503 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.4845. Min Act: -0.1700
Data Index: 3244205 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.4532. Min Act: -0.1700
Data Index: 463161 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.5157. Min Act: -0.1700
Data Index: 5704322 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.4845. Min Act: -0.1700
Data Index: 3849547 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6407. Min Range: -4.6407
Max Act: 4.4845. Min Act: -0.1700
Data Index: 1498846 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19