Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3523 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0257. Min Range: -7.0257
Max Act: 7.0257. Min Act: -0.1700
Data Index: 2004261 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.9007. Min Act: -0.1700
Data Index: 7122143 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.8694. Min Act: -0.1700
Data Index: 6734377 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.8694. Min Act: -0.1700
Data Index: 1720239 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.8694. Min Act: -0.1700
Data Index: 3645762 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.8382. Min Act: -0.1700
Data Index: 2089161 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.8382. Min Act: -0.1700
Data Index: 2089162 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.8069. Min Act: -0.1700
Data Index: 5908600 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7757. Min Act: -0.1700
Data Index: 6187337 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7757. Min Act: -0.1700
Data Index: 8535902 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7757. Min Act: -0.1700
Data Index: 639891 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7757. Min Act: -0.1700
Data Index: 4477592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7132. Min Act: -0.1700
Data Index: 3216590 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7444. Min Act: -0.1700
Data Index: 7909956 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7444. Min Act: -0.1700
Data Index: 4315712 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7444. Min Act: -0.1700
Data Index: 3178126 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7444. Min Act: -0.1700
Data Index: 8764749 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7444. Min Act: -0.1700
Data Index: 5127387 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7132. Min Act: -0.1700
Data Index: 792761 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0257. Min Range: -7.0257
Max Act: 6.7132. Min Act: -0.1700
Data Index: 238035 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19