Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.7754. Min Act: -0.1700
Data Index: 3134775 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.5254. Min Act: -0.1700
Data Index: 2358802 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.4629. Min Act: -0.1700
Data Index: 6713389 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.3379. Min Act: -0.1700
Data Index: 8450456 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.2441. Min Act: -0.1700
Data Index: 4387220 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.2129. Min Act: -0.1700
Data Index: 7818258 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.2129. Min Act: -0.1700
Data Index: 2917035 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.1191. Min Act: -0.1700
Data Index: 506648 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.1504. Min Act: -0.1700
Data Index: 3677299 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.0566. Min Act: -0.1700
Data Index: 6706804 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.0879. Min Act: -0.1700
Data Index: 8457899 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.0566. Min Act: -0.1700
Data Index: 6929370 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.0566. Min Act: -0.1700
Data Index: 4580131 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.0566. Min Act: -0.1700
Data Index: 4281709 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.0879. Min Act: -0.1700
Data Index: 807577 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.0566. Min Act: -0.1700
Data Index: 5767926 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.0566. Min Act: -0.1700
Data Index: 738638 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.0254. Min Act: -0.1700
Data Index: 5021780 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7754. Min Range: -5.7754
Max Act: 5.0254. Min Act: -0.1700
Data Index: 6463164 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7754. Min Range: -5.7754
Max Act: 4.9629. Min Act: -0.1700
Data Index: 374338 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19