Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2388 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3676. Min Range: -4.3676
Max Act: 4.3676. Min Act: -0.1700
Data Index: 282054 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3676. Min Range: -4.3676
Max Act: 4.2426. Min Act: -0.1700
Data Index: 1379902 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3676. Min Range: -4.3676
Max Act: 4.1176. Min Act: -0.1700
Data Index: 5885986 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3676. Min Range: -4.3676
Max Act: 4.0551. Min Act: -0.1700
Data Index: 2500047 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3676. Min Range: -4.3676
Max Act: 4.0551. Min Act: -0.1700
Data Index: 483404 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.9925. Min Act: -0.1700
Data Index: 388581 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.9925. Min Act: -0.1700
Data Index: 2525404 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.9300. Min Act: -0.1700
Data Index: 5289806 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.9613. Min Act: -0.1700
Data Index: 4623135 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.9613. Min Act: -0.1700
Data Index: 4951861 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.9300. Min Act: -0.1700
Data Index: 1544173 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.8987. Min Act: -0.1700
Data Index: 5009490 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.8987. Min Act: -0.1700
Data Index: 5719353 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.8987. Min Act: -0.1700
Data Index: 1778245 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.8987. Min Act: -0.1700
Data Index: 4939513 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.8675. Min Act: -0.1700
Data Index: 3557131 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.8675. Min Act: -0.1700
Data Index: 948154 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.8675. Min Act: -0.1700
Data Index: 7101202 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.8675. Min Act: -0.1700
Data Index: 5719376 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3676. Min Range: -4.3676
Max Act: 3.8675. Min Act: -0.1700
Data Index: 2504412 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19