Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5533 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3295. Min Range: -6.3295
Max Act: 6.3295. Min Act: -0.1700
Data Index: 239696 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3295. Min Range: -6.3295
Max Act: 6.2358. Min Act: -0.1700
Data Index: 416571 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3295. Min Range: -6.3295
Max Act: 6.2045. Min Act: -0.1700
Data Index: 3579291 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3295. Min Range: -6.3295
Max Act: 6.1420. Min Act: -0.1700
Data Index: 8780596 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3295. Min Range: -6.3295
Max Act: 6.1420. Min Act: -0.1700
Data Index: 416574 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3295. Min Range: -6.3295
Max Act: 6.0795. Min Act: -0.1700
Data Index: 7480778 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3295. Min Range: -6.3295
Max Act: 6.0795. Min Act: -0.1700
Data Index: 2938688 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3295. Min Range: -6.3295
Max Act: 6.0170. Min Act: -0.1700
Data Index: 4340965 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3295. Min Range: -6.3295
Max Act: 6.0170. Min Act: -0.1700
Data Index: 6813020 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3295. Min Range: -6.3295
Max Act: 6.0170. Min Act: -0.1700
Data Index: 1828027 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3295. Min Range: -6.3295
Max Act: 5.9858. Min Act: -0.1700
Data Index: 3073646 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3295. Min Range: -6.3295
Max Act: 5.9858. Min Act: -0.1700
Data Index: 5325103 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3295. Min Range: -6.3295
Max Act: 5.9858. Min Act: -0.1700
Data Index: 5111085 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3295. Min Range: -6.3295
Max Act: 5.9545. Min Act: -0.1700
Data Index: 2347237 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3295. Min Range: -6.3295
Max Act: 5.9233. Min Act: -0.1700
Data Index: 6706297 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3295. Min Range: -6.3295
Max Act: 5.9545. Min Act: -0.1700
Data Index: 4049401 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3295. Min Range: -6.3295
Max Act: 5.9233. Min Act: -0.1700
Data Index: 968292 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3295. Min Range: -6.3295
Max Act: 5.9233. Min Act: -0.1700
Data Index: 3482200 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3295. Min Range: -6.3295
Max Act: 5.9233. Min Act: -0.1700
Data Index: 2918460 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3295. Min Range: -6.3295
Max Act: 5.8920. Min Act: -0.1700
Data Index: 3236961 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19