Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.3119. Min Act: -0.1700
Data Index: 2651368 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.2494. Min Act: -0.1700
Data Index: 7958528 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.2181. Min Act: -0.1700
Data Index: 30336 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.1244. Min Act: -0.1700
Data Index: 5512341 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.0931. Min Act: -0.1700
Data Index: 8635433 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.0619. Min Act: -0.1700
Data Index: 8182317 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.0306. Min Act: -0.1700
Data Index: 531193 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.0619. Min Act: -0.1700
Data Index: 113223 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.0306. Min Act: -0.1700
Data Index: 7776359 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9994. Min Act: -0.1700
Data Index: 6354633 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9994. Min Act: -0.1700
Data Index: 6304129 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9681. Min Act: -0.1700
Data Index: 5074243 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9681. Min Act: -0.1700
Data Index: 7863892 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9994. Min Act: -0.1700
Data Index: 33751 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9369. Min Act: -0.1700
Data Index: 6296338 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9056. Min Act: -0.1700
Data Index: 2665921 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9056. Min Act: -0.1700
Data Index: 863406 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9056. Min Act: -0.1700
Data Index: 5552778 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9056. Min Act: -0.1699
Data Index: 7101683 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.8119. Min Act: -0.1700
Data Index: 6661604 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19