Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.2209. Min Act: -0.1700
Data Index: 2227563 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.2209. Min Act: -0.1700
Data Index: 4630101 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.1897. Min Act: -0.1700
Data Index: 2003675 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.1584. Min Act: -0.1700
Data Index: 6682779 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.1584. Min Act: -0.1700
Data Index: 6459334 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0959. Min Act: -0.1700
Data Index: 6344480 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.1272. Min Act: -0.1700
Data Index: 3125815 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0647. Min Act: -0.1700
Data Index: 5566337 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0959. Min Act: -0.1700
Data Index: 4137900 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0959. Min Act: -0.1700
Data Index: 7379510 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0647. Min Act: -0.1700
Data Index: 3984498 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0647. Min Act: -0.1700
Data Index: 2850767 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0334. Min Act: -0.1700
Data Index: 841001 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0647. Min Act: -0.1700
Data Index: 3493131 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0022. Min Act: -0.1700
Data Index: 1621153 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0022. Min Act: -0.1700
Data Index: 3683776 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0334. Min Act: -0.1700
Data Index: 3449665 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0334. Min Act: -0.1700
Data Index: 5788887 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0022. Min Act: -0.1700
Data Index: 2974764 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2209. Min Range: -4.2209
Max Act: 4.0022. Min Act: -0.1700
Data Index: 507114 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19