Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4233 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2608. Min Range: -4.2608
Max Act: 4.2608. Min Act: -0.1700
Data Index: 4158149 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2608. Min Range: -4.2608
Max Act: 4.0733. Min Act: -0.1700
Data Index: 607307 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2608. Min Range: -4.2608
Max Act: 4.0420. Min Act: -0.1700
Data Index: 5383952 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.9795. Min Act: -0.1700
Data Index: 2075388 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.9795. Min Act: -0.1700
Data Index: 8473853 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.9170. Min Act: -0.1700
Data Index: 3739200 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.9170. Min Act: -0.1700
Data Index: 7918015 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.8701. Min Act: -0.1700
Data Index: 5874166 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.8388. Min Act: -0.1700
Data Index: 8015224 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.8388. Min Act: -0.1700
Data Index: 3212736 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.8231. Min Act: -0.1700
Data Index: 5772036 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.8231. Min Act: -0.1700
Data Index: 8047720 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.8075. Min Act: -0.1700
Data Index: 1355961 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.8075. Min Act: -0.1700
Data Index: 4558025 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.7762. Min Act: -0.1700
Data Index: 1285425 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.7919. Min Act: -0.1700
Data Index: 5154759 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.7450. Min Act: -0.1700
Data Index: 5512206 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.7606. Min Act: -0.1700
Data Index: 1441468 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.7606. Min Act: -0.1700
Data Index: 511512 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2608. Min Range: -4.2608
Max Act: 3.7606. Min Act: -0.1700
Data Index: 2550448 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19