Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1384 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0392. Min Range: -6.0392
Max Act: 6.0392. Min Act: -0.1700
Data Index: 2021706 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0392. Min Range: -6.0392
Max Act: 6.0079. Min Act: -0.1700
Data Index: 1984023 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.9767. Min Act: -0.1700
Data Index: 2839609 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.9142. Min Act: -0.1700
Data Index: 8275313 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.7579. Min Act: -0.1700
Data Index: 7150220 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.7579. Min Act: -0.1700
Data Index: 6851945 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6954. Min Act: -0.1700
Data Index: 8362531 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.7267. Min Act: -0.1700
Data Index: 8224739 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6954. Min Act: -0.1700
Data Index: 1588 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6642. Min Act: -0.1700
Data Index: 8054663 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.7267. Min Act: -0.1700
Data Index: 7010044 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.7267. Min Act: -0.1700
Data Index: 7149003 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6954. Min Act: -0.1700
Data Index: 8062582 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6954. Min Act: -0.1700
Data Index: 2068898 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1246155 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6329. Min Act: -0.1700
Data Index: 156637 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6017. Min Act: -0.1700
Data Index: 1867687 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6017. Min Act: -0.1700
Data Index: 6696689 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6329. Min Act: -0.1700
Data Index: 6657996 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0392. Min Range: -6.0392
Max Act: 5.6017. Min Act: -0.1700
Data Index: 479955 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19