Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.9278. Min Act: -0.1700
Data Index: 5874818 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.5216. Min Act: -0.1700
Data Index: 4512248 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.4903. Min Act: -0.1700
Data Index: 4541011 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.4591. Min Act: -0.1700
Data Index: 343715 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.3653. Min Act: -0.1700
Data Index: 4497772 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.3653. Min Act: -0.1700
Data Index: 4646985 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.3341. Min Act: -0.1700
Data Index: 2942334 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.3653. Min Act: -0.1700
Data Index: 4508935 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.3341. Min Act: -0.1700
Data Index: 2032974 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.3028. Min Act: -0.1700
Data Index: 6356205 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.2716. Min Act: -0.1700
Data Index: 3432257 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.3028. Min Act: -0.1700
Data Index: 2766624 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.2716. Min Act: -0.1700
Data Index: 7770288 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.2403. Min Act: -0.1700
Data Index: 1572529 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.2091. Min Act: -0.1700
Data Index: 4876560 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.1466. Min Act: -0.1700
Data Index: 2155457 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.1466. Min Act: -0.1700
Data Index: 8551225 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.1153. Min Act: -0.1700
Data Index: 7401800 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.1153. Min Act: -0.1700
Data Index: 525499 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.1153. Min Act: -0.1700
Data Index: 5826188 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19