Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0634. Min Act: -0.1700
Data Index: 3135495 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0634. Min Act: -0.1700
Data Index: 8783494 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0634. Min Act: -0.1700
Data Index: 6832883 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0634. Min Act: -0.1700
Data Index: 723496 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0634. Min Act: -0.1700
Data Index: 7343680 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0634. Min Act: -0.1700
Data Index: 4116126 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0466. Min Act: -0.1700
Data Index: 1671757 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0297. Min Act: -0.1700
Data Index: 3380739 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0297. Min Act: -0.1700
Data Index: 8713657 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0129. Min Act: -0.1700
Data Index: 2114871 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0466. Min Act: -0.1700
Data Index: 3521913 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0466. Min Act: -0.1700
Data Index: 1019823 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0129. Min Act: -0.1700
Data Index: 1264071 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0129. Min Act: -0.1700
Data Index: 8645873 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0129. Min Act: -0.1700
Data Index: 5838921 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0634. Min Range: -2.0634
Max Act: 2.0129. Min Act: -0.1700
Data Index: 1247562 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0634. Min Range: -2.0634
Max Act: 1.9790. Min Act: -0.1700
Data Index: 1454029 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0634. Min Range: -2.0634
Max Act: 1.9960. Min Act: -0.1700
Data Index: 3325437 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0634. Min Range: -2.0634
Max Act: 1.9960. Min Act: -0.1700
Data Index: 5586764 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0634. Min Range: -2.0634
Max Act: 1.9960. Min Act: -0.1700
Data Index: 8781322 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19