Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1403 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.7267. Min Act: -0.1700
Data Index: 3840941 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.7267. Min Act: -0.1700
Data Index: 1753605 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.6954. Min Act: -0.1700
Data Index: 641155 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.6329. Min Act: -0.1700
Data Index: 8625520 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.5079. Min Act: -0.1700
Data Index: 748990 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.5079. Min Act: -0.1700
Data Index: 3563805 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.5391. Min Act: -0.1700
Data Index: 7209730 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.5079. Min Act: -0.1700
Data Index: 7646141 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4766. Min Act: -0.1700
Data Index: 69164 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4766. Min Act: -0.1700
Data Index: 1811249 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4766. Min Act: -0.1700
Data Index: 3522503 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4454. Min Act: -0.1700
Data Index: 5809268 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4141. Min Act: -0.1700
Data Index: 1667648 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4454. Min Act: -0.1700
Data Index: 8217143 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4454. Min Act: -0.1700
Data Index: 1700134 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4454. Min Act: -0.1700
Data Index: 6287025 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4141. Min Act: -0.1700
Data Index: 3661030 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4454. Min Act: -0.1700
Data Index: 371248 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4454. Min Act: -0.1700
Data Index: 8218364 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7267. Min Range: -4.7267
Max Act: 4.4454. Min Act: -0.1700
Data Index: 536793 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19