Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 916 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1252. Min Range: -6.1252
Max Act: 6.1252. Min Act: -0.1700
Data Index: 5692429 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1252. Min Range: -6.1252
Max Act: 6.0627. Min Act: -0.1700
Data Index: 202326 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1252. Min Range: -6.1252
Max Act: 6.0315. Min Act: -0.1700
Data Index: 5692426 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.9690. Min Act: -0.1700
Data Index: 333050 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.9377. Min Act: -0.1700
Data Index: 1572005 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.9377. Min Act: -0.1700
Data Index: 5692422 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.9065. Min Act: -0.1700
Data Index: 2645833 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.8752. Min Act: -0.1700
Data Index: 5692423 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.8440. Min Act: -0.1700
Data Index: 8039691 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.8127. Min Act: -0.1700
Data Index: 4573589 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.7815. Min Act: -0.1700
Data Index: 6783151 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.8127. Min Act: -0.1700
Data Index: 33748 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.8127. Min Act: -0.1700
Data Index: 5439230 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.7815. Min Act: -0.1700
Data Index: 5692425 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.7190. Min Act: -0.1700
Data Index: 8014877 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.7502. Min Act: -0.1700
Data Index: 1236736 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.7502. Min Act: -0.1700
Data Index: 3441215 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.6877. Min Act: -0.1700
Data Index: 6957887 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.7190. Min Act: -0.1700
Data Index: 2251968 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1252. Min Range: -6.1252
Max Act: 5.6565. Min Act: -0.1700
Data Index: 931407 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19