Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0442. Min Range: -5.0442
Max Act: 5.0442. Min Act: -0.1700
Data Index: 2596327 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.6692. Min Act: -0.1700
Data Index: 6980623 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.5129. Min Act: -0.1700
Data Index: 6675345 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.5129. Min Act: -0.1700
Data Index: 8179938 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4817. Min Act: -0.1700
Data Index: 2784027 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4504. Min Act: -0.1700
Data Index: 1052436 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4504. Min Act: -0.1700
Data Index: 4831437 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4504. Min Act: -0.1700
Data Index: 4711397 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4504. Min Act: -0.1700
Data Index: 5876368 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4504. Min Act: -0.1700
Data Index: 3213986 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4504. Min Act: -0.1700
Data Index: 1414411 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4192. Min Act: -0.1700
Data Index: 3112921 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4192. Min Act: -0.1700
Data Index: 136668 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4192. Min Act: -0.1700
Data Index: 7306940 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4192. Min Act: -0.1700
Data Index: 2536755 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.4192. Min Act: -0.1700
Data Index: 4916242 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.3879. Min Act: -0.1700
Data Index: 2036391 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.3879. Min Act: -0.1700
Data Index: 6883336 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.3879. Min Act: -0.1700
Data Index: 4554744 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0442. Min Range: -5.0442
Max Act: 4.3567. Min Act: -0.1700
Data Index: 5371483 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19