Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4371 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0151. Min Range: -5.0151
Max Act: 5.0151. Min Act: -0.1700
Data Index: 4398771 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.7964. Min Act: -0.1700
Data Index: 5067291 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.7339. Min Act: -0.1700
Data Index: 7020320 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.7339. Min Act: -0.1700
Data Index: 5070982 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.6714. Min Act: -0.1700
Data Index: 47300 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.6401. Min Act: -0.1700
Data Index: 305507 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.6401. Min Act: -0.1700
Data Index: 6965505 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.6089. Min Act: -0.1700
Data Index: 8266967 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.5464. Min Act: -0.1700
Data Index: 4452826 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.5151. Min Act: -0.1700
Data Index: 7790148 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.5151. Min Act: -0.1700
Data Index: 1391098 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.4839. Min Act: -0.1700
Data Index: 7279435 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.4839. Min Act: -0.1700
Data Index: 8098839 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.4839. Min Act: -0.1700
Data Index: 8105041 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.4526. Min Act: -0.1700
Data Index: 2030205 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.4526. Min Act: -0.1700
Data Index: 3949441 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.4214. Min Act: -0.1700
Data Index: 5304821 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.4214. Min Act: -0.1700
Data Index: 5014931 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.4214. Min Act: -0.1700
Data Index: 566325 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0151. Min Range: -5.0151
Max Act: 4.4214. Min Act: -0.1700
Data Index: 4867365 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19