Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 772 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.5025. Min Act: -0.1700
Data Index: 8224474 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.3775. Min Act: -0.1700
Data Index: 3647256 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.3775. Min Act: -0.1700
Data Index: 251442 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.3150. Min Act: -0.1700
Data Index: 1746309 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.3150. Min Act: -0.1700
Data Index: 5631520 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.3463. Min Act: -0.1700
Data Index: 7955066 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.3775. Min Act: -0.1700
Data Index: 7618935 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.2525. Min Act: -0.1700
Data Index: 3845618 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.2213. Min Act: -0.1700
Data Index: 4924144 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.2213. Min Act: -0.1700
Data Index: 7957153 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.1275. Min Act: -0.1700
Data Index: 5601313 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.1588. Min Act: -0.1700
Data Index: 4145932 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.0963. Min Act: -0.1700
Data Index: 7455976 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.0650. Min Act: -0.1700
Data Index: 6619800 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.0963. Min Act: -0.1700
Data Index: 8587023 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.1275. Min Act: -0.1700
Data Index: 5722944 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5025. Min Range: -6.5025
Max Act: 6.0025. Min Act: -0.1700
Data Index: 7473073 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5025. Min Range: -6.5025
Max Act: 5.9713. Min Act: -0.1700
Data Index: 1561308 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5025. Min Range: -6.5025
Max Act: 5.9713. Min Act: -0.1700
Data Index: 2690225 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5025. Min Range: -6.5025
Max Act: 5.9400. Min Act: -0.1700
Data Index: 8657607 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19