Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1431. Min Range: -5.1431
Max Act: 5.1431. Min Act: -0.1700
Data Index: 6316004 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1431. Min Range: -5.1431
Max Act: 5.0493. Min Act: -0.1700
Data Index: 6724681 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.9556. Min Act: -0.1700
Data Index: 2583908 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.9556. Min Act: -0.1700
Data Index: 4012870 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.8931. Min Act: -0.1700
Data Index: 5525154 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.8618. Min Act: -0.1700
Data Index: 2437007 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.8618. Min Act: -0.1700
Data Index: 8409428 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.8306. Min Act: -0.1700
Data Index: 1066974 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.8306. Min Act: -0.1700
Data Index: 3611281 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.8306. Min Act: -0.1700
Data Index: 4935734 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.8306. Min Act: -0.1700
Data Index: 4102824 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.7993. Min Act: -0.1700
Data Index: 5179414 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.7681. Min Act: -0.1700
Data Index: 73397 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.7993. Min Act: -0.1700
Data Index: 832210 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.7993. Min Act: -0.1700
Data Index: 7566443 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.8306. Min Act: -0.1700
Data Index: 7359838 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.7993. Min Act: -0.1700
Data Index: 2833682 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.7993. Min Act: -0.1700
Data Index: 572639 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.7681. Min Act: -0.1700
Data Index: 3796219 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1431. Min Range: -5.1431
Max Act: 4.7681. Min Act: -0.1700
Data Index: 6281453 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19