Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0258. Min Range: -4.0258
Max Act: 4.0258. Min Act: -0.1700
Data Index: 5517069 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0258. Min Range: -4.0258
Max Act: 4.0101. Min Act: -0.1700
Data Index: 1847476 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0258. Min Range: -4.0258
Max Act: 4.0101. Min Act: -0.1700
Data Index: 5317650 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.9789. Min Act: -0.1700
Data Index: 5402197 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.9476. Min Act: -0.1700
Data Index: 6139716 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.9164. Min Act: -0.1700
Data Index: 6405624 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.9007. Min Act: -0.1700
Data Index: 6162386 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.9320. Min Act: -0.1700
Data Index: 4417718 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.9007. Min Act: -0.1700
Data Index: 5768979 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.8851. Min Act: -0.1700
Data Index: 2351779 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.8851. Min Act: -0.1700
Data Index: 3968615 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.9007. Min Act: -0.1700
Data Index: 8503789 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.8851. Min Act: -0.1700
Data Index: 4254663 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.8695. Min Act: -0.1700
Data Index: 7214183 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.8851. Min Act: -0.1700
Data Index: 5655081 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.8851. Min Act: -0.1700
Data Index: 2775243 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.8382. Min Act: -0.1700
Data Index: 8646531 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.8538. Min Act: -0.1700
Data Index: 8686928 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.8538. Min Act: -0.1700
Data Index: 5465135 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0258. Min Range: -4.0258
Max Act: 3.8226. Min Act: -0.1700
Data Index: 5061596 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19