Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.8260. Min Act: -0.1700
Data Index: 2086115 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.5760. Min Act: -0.1700
Data Index: 4117357 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.5135. Min Act: -0.1700
Data Index: 4117366 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.4198. Min Act: -0.1700
Data Index: 8240051 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.3260. Min Act: -0.1700
Data Index: 7546023 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.3573. Min Act: -0.1700
Data Index: 6620336 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.3260. Min Act: -0.1700
Data Index: 7995269 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.3260. Min Act: -0.1700
Data Index: 2081364 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.3260. Min Act: -0.1700
Data Index: 3027392 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.2948. Min Act: -0.1700
Data Index: 7293886 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.2948. Min Act: -0.1700
Data Index: 7426452 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.2635. Min Act: -0.1700
Data Index: 5551225 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.2635. Min Act: -0.1700
Data Index: 6470403 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.2323. Min Act: -0.1700
Data Index: 8119623 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.2323. Min Act: -0.1700
Data Index: 378560 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.2010. Min Act: -0.1700
Data Index: 1426073 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.2010. Min Act: -0.1700
Data Index: 8064301 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.1698. Min Act: -0.1700
Data Index: 8292290 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.1698. Min Act: -0.1700
Data Index: 3239726 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8260. Min Range: -5.8260
Max Act: 5.1698. Min Act: -0.1700
Data Index: 3673507 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19