Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2318 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.8217. Min Act: -0.1700
Data Index: 8208922 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.6967. Min Act: -0.1700
Data Index: 3168096 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.6654. Min Act: -0.1700
Data Index: 2956812 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.7279. Min Act: -0.1700
Data Index: 3964109 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.6029. Min Act: -0.1700
Data Index: 327792 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.6029. Min Act: -0.1700
Data Index: 4480775 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.5717. Min Act: -0.1700
Data Index: 1646969 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.6342. Min Act: -0.1700
Data Index: 4514781 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.5717. Min Act: -0.1700
Data Index: 4199355 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.5717. Min Act: -0.1700
Data Index: 4884268 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.4779. Min Act: -0.1700
Data Index: 8026764 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.5092. Min Act: -0.1700
Data Index: 4633571 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.4467. Min Act: -0.1698
Data Index: 5742284 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.5092. Min Act: -0.1700
Data Index: 1492480 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.5092. Min Act: -0.1700
Data Index: 4655895 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.5404. Min Act: -0.1700
Data Index: 780546 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.4467. Min Act: -0.1700
Data Index: 7306400 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.4779. Min Act: -0.1700
Data Index: 7605526 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.4467. Min Act: -0.1700
Data Index: 5803718 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8217. Min Range: -6.8217
Max Act: 6.4467. Min Act: -0.1700
Data Index: 2492701 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19