Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5135 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.3878. Min Act: -0.1700
Data Index: 2683553 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.3565. Min Act: -0.1700
Data Index: 1804431 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.3565. Min Act: -0.1700
Data Index: 3233908 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.3253. Min Act: -0.1700
Data Index: 231861 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.3253. Min Act: -0.1700
Data Index: 467275 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.3253. Min Act: -0.1700
Data Index: 2886850 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.2628. Min Act: -0.1700
Data Index: 1190463 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.2940. Min Act: -0.1700
Data Index: 5139617 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.2628. Min Act: -0.1700
Data Index: 7595737 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.2003. Min Act: -0.1700
Data Index: 7056108 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.2003. Min Act: -0.1700
Data Index: 6443603 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.1690. Min Act: -0.1700
Data Index: 4898323 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.1690. Min Act: -0.1700
Data Index: 1378947 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.1378. Min Act: -0.1700
Data Index: 1815163 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.1378. Min Act: -0.1700
Data Index: 1606776 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.1378. Min Act: -0.1698
Data Index: 5476924 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.1378. Min Act: -0.1700
Data Index: 472586 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.1378. Min Act: -0.1700
Data Index: 192206 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.1065. Min Act: -0.1700
Data Index: 5590510 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3878. Min Range: -5.3878
Max Act: 5.1378. Min Act: -0.1700
Data Index: 440920 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19