Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1591 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0007. Min Range: -6.0007
Max Act: 6.0007. Min Act: -0.1700
Data Index: 3585398 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.9069. Min Act: -0.1700
Data Index: 1347988 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.7819. Min Act: -0.1700
Data Index: 7190800 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.7194. Min Act: -0.1700
Data Index: 695844 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.6882. Min Act: -0.1700
Data Index: 3476259 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.6569. Min Act: -0.1700
Data Index: 2441678 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.6257. Min Act: -0.1700
Data Index: 7576593 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.6569. Min Act: -0.1700
Data Index: 1021955 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.6257. Min Act: -0.1700
Data Index: 7418112 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.6257. Min Act: -0.1700
Data Index: 2320879 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.6257. Min Act: -0.1700
Data Index: 432794 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.5944. Min Act: -0.1700
Data Index: 7890119 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.6257. Min Act: -0.1700
Data Index: 5533618 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.5944. Min Act: -0.1700
Data Index: 1872278 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.5319. Min Act: -0.1700
Data Index: 7547084 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.5632. Min Act: -0.1700
Data Index: 664053 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.5632. Min Act: -0.1700
Data Index: 4254383 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.5632. Min Act: -0.1700
Data Index: 3466797 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.5632. Min Act: -0.1700
Data Index: 643720 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0007. Min Range: -6.0007
Max Act: 5.5632. Min Act: -0.1700
Data Index: 2213661 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19