Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.8911. Min Act: -0.1700
Data Index: 2326167 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7347. Min Act: -0.1700
Data Index: 8036469 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7347. Min Act: -0.1700
Data Index: 5236688 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7347. Min Act: -0.1700
Data Index: 4564429 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7347. Min Act: -0.1700
Data Index: 5720051 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7035. Min Act: -0.1700
Data Index: 6634783 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6722. Min Act: -0.1700
Data Index: 1342513 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6409. Min Act: -0.1700
Data Index: 8386116 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6409. Min Act: -0.1700
Data Index: 6646217 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6096. Min Act: -0.1700
Data Index: 707297 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6096. Min Act: -0.1700
Data Index: 4821984 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.5939. Min Act: -0.1700
Data Index: 499258 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.5783. Min Act: -0.1700
Data Index: 3718995 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6096. Min Act: -0.1700
Data Index: 1452595 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.5939. Min Act: -0.1700
Data Index: 6527899 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.5626. Min Act: -0.1700
Data Index: 5213912 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.5626. Min Act: -0.1700
Data Index: 7080745 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.5626. Min Act: -0.1700
Data Index: 5035289 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.5470. Min Act: -0.1700
Data Index: 2421006 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.5000. Min Act: -0.1700
Data Index: 4439345 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19