Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5017. Min Range: -6.5017
Max Act: 6.5017. Min Act: -0.1700
Data Index: 6672699 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5017. Min Range: -6.5017
Max Act: 6.4080. Min Act: -0.1700
Data Index: 8541410 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5017. Min Range: -6.5017
Max Act: 6.3767. Min Act: -0.1700
Data Index: 6672698 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5017. Min Range: -6.5017
Max Act: 6.1580. Min Act: -0.1700
Data Index: 4011537 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5017. Min Range: -6.5017
Max Act: 6.0642. Min Act: -0.1700
Data Index: 7734290 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.8767. Min Act: -0.1700
Data Index: 2985302 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.8455. Min Act: -0.1700
Data Index: 3663354 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.8767. Min Act: -0.1700
Data Index: 620820 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.9080. Min Act: -0.1700
Data Index: 4736953 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.8142. Min Act: -0.1700
Data Index: 6064676 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.8455. Min Act: -0.1700
Data Index: 6644052 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.7830. Min Act: -0.1700
Data Index: 7856052 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.7830. Min Act: -0.1700
Data Index: 5712510 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.7205. Min Act: -0.1700
Data Index: 6569127 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.7205. Min Act: -0.1700
Data Index: 7055690 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.6892. Min Act: -0.1700
Data Index: 7181970 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.6892. Min Act: -0.1700
Data Index: 6893410 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.6892. Min Act: -0.1700
Data Index: 5317730 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.6892. Min Act: -0.1700
Data Index: 3216130 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5017. Min Range: -6.5017
Max Act: 5.6580. Min Act: -0.1700
Data Index: 6018307 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19