Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 944 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.1378. Min Act: -0.1700
Data Index: 1496255 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.1378. Min Act: -0.1700
Data Index: 4378231 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0753. Min Act: -0.1700
Data Index: 2650851 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0441. Min Act: -0.1700
Data Index: 2214338 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0441. Min Act: -0.1700
Data Index: 7413154 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0128. Min Act: -0.1700
Data Index: 7572020 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0441. Min Act: -0.1700
Data Index: 8281220 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0753. Min Act: -0.1700
Data Index: 261847 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0441. Min Act: -0.1700
Data Index: 7203857 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0441. Min Act: -0.1700
Data Index: 796795 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1378. Min Range: -5.1378
Max Act: 4.9816. Min Act: -0.1700
Data Index: 6623168 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0128. Min Act: -0.1700
Data Index: 6165526 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0441. Min Act: -0.1700
Data Index: 5880236 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0128. Min Act: -0.1700
Data Index: 4543368 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0128. Min Act: -0.1700
Data Index: 1191806 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0128. Min Act: -0.1700
Data Index: 1718449 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1378. Min Range: -5.1378
Max Act: 4.9816. Min Act: -0.1700
Data Index: 1164100 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0128. Min Act: -0.1700
Data Index: 1640356 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0128. Min Act: -0.1700
Data Index: 395487 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1378. Min Range: -5.1378
Max Act: 5.0128. Min Act: -0.1700
Data Index: 4053909 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19