Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5141. Min Range: -12.5141
Max Act: 12.5141. Min Act: -0.1700
Data Index: 6742700 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5141. Min Range: -12.5141
Max Act: 12.3891. Min Act: -0.1700
Data Index: 288815 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.6391. Min Act: -0.1700
Data Index: 6614836 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.5766. Min Act: -0.1700
Data Index: 7747763 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.4516. Min Act: -0.1700
Data Index: 1711087 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.5141. Min Act: -0.1700
Data Index: 4071641 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.4516. Min Act: -0.1700
Data Index: 7887630 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.4516. Min Act: -0.1700
Data Index: 7410773 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.4516. Min Act: -0.1700
Data Index: 7709532 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.3891. Min Act: -0.1700
Data Index: 3407140 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.3891. Min Act: -0.1700
Data Index: 2558393 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.3891. Min Act: -0.1700
Data Index: 2840678 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.3891. Min Act: -0.1700
Data Index: 7085226 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.3266. Min Act: -0.1700
Data Index: 4866712 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.3266. Min Act: -0.1700
Data Index: 1799029 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.3891. Min Act: -0.1700
Data Index: 2497380 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.2641. Min Act: -0.1700
Data Index: 6831018 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.2016. Min Act: -0.1700
Data Index: 5063172 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.2641. Min Act: -0.1700
Data Index: 1173758 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5141. Min Range: -12.5141
Max Act: 11.2641. Min Act: -0.1700
Data Index: 3692392 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19