Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4207 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.3189. Min Act: -0.1700
Data Index: 4046198 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.2564. Min Act: -0.1700
Data Index: 2477432 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.1939. Min Act: -0.1700
Data Index: 6942857 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.1939. Min Act: -0.1700
Data Index: 7324165 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.1314. Min Act: -0.1700
Data Index: 6494662 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.0376. Min Act: -0.1700
Data Index: 5224923 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.0376. Min Act: -0.1700
Data Index: 7363539 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.0376. Min Act: -0.1700
Data Index: 3092651 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.0063. Min Act: -0.1700
Data Index: 1452645 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.0063. Min Act: -0.1700
Data Index: 3878220 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3189. Min Range: -4.3189
Max Act: 4.0063. Min Act: -0.1700
Data Index: 6502297 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3189. Min Range: -4.3189
Max Act: 3.9751. Min Act: -0.1700
Data Index: 2809841 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3189. Min Range: -4.3189
Max Act: 3.9751. Min Act: -0.1700
Data Index: 3126676 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3189. Min Range: -4.3189
Max Act: 3.9438. Min Act: -0.1700
Data Index: 4834319 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3189. Min Range: -4.3189
Max Act: 3.9438. Min Act: -0.1700
Data Index: 716806 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3189. Min Range: -4.3189
Max Act: 3.9438. Min Act: -0.1700
Data Index: 8434185 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3189. Min Range: -4.3189
Max Act: 3.9438. Min Act: -0.1700
Data Index: 7461527 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3189. Min Range: -4.3189
Max Act: 3.9438. Min Act: -0.1700
Data Index: 1606738 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3189. Min Range: -4.3189
Max Act: 3.9125. Min Act: -0.1700
Data Index: 4486543 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3189. Min Range: -4.3189
Max Act: 3.9125. Min Act: -0.1700
Data Index: 7064361 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19