Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3871 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.6022. Min Act: -0.1700
Data Index: 1890980 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5865. Min Act: -0.1700
Data Index: 4720694 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5865. Min Act: -0.1700
Data Index: 8462691 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5552. Min Act: -0.1700
Data Index: 7996242 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5552. Min Act: -0.1700
Data Index: 4256471 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5552. Min Act: -0.1700
Data Index: 1675549 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5552. Min Act: -0.1700
Data Index: 3336772 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5708. Min Act: -0.1700
Data Index: 7996238 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5552. Min Act: -0.1700
Data Index: 5098349 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5395. Min Act: -0.1700
Data Index: 2523311 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5395. Min Act: -0.1700
Data Index: 710306 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5239. Min Act: -0.1700
Data Index: 5634821 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5082. Min Act: -0.1700
Data Index: 4278337 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5082. Min Act: -0.1700
Data Index: 2389495 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.5082. Min Act: -0.1700
Data Index: 7113694 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.4926. Min Act: -0.1700
Data Index: 6279601 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.4769. Min Act: -0.1700
Data Index: 1817617 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.4926. Min Act: -0.1700
Data Index: 4522197 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.4769. Min Act: -0.1700
Data Index: 3757805 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6022. Min Range: -3.6022
Max Act: 3.4769. Min Act: -0.1700
Data Index: 3771187 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19