Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3649 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1128. Min Range: -8.1128
Max Act: 8.1128. Min Act: -0.1700
Data Index: 5333237 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1128. Min Range: -8.1128
Max Act: 8.0503. Min Act: -0.1700
Data Index: 7801901 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.8941. Min Act: -0.1700
Data Index: 1350569 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.7378. Min Act: -0.1700
Data Index: 1606882 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.7378. Min Act: -0.1700
Data Index: 1842207 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.6128. Min Act: -0.1700
Data Index: 8778182 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.6128. Min Act: -0.1700
Data Index: 4278236 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.6128. Min Act: -0.1700
Data Index: 2405514 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.6128. Min Act: -0.1700
Data Index: 4462169 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.5816. Min Act: -0.1700
Data Index: 1241685 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.5503. Min Act: -0.1700
Data Index: 4321022 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.5503. Min Act: -0.1700
Data Index: 8785951 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.5503. Min Act: -0.1700
Data Index: 7754620 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.5503. Min Act: -0.1700
Data Index: 1950436 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.5191. Min Act: -0.1700
Data Index: 5759339 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.5191. Min Act: -0.1700
Data Index: 6364876 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.5191. Min Act: -0.1700
Data Index: 1958803 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.5191. Min Act: -0.1700
Data Index: 2258167 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.4878. Min Act: -0.1700
Data Index: 1291561 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1128. Min Range: -8.1128
Max Act: 7.4878. Min Act: -0.1700
Data Index: 1007452 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19