Model: None
Dataset: The Pile
Neuron 1496 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.7968. Min Act: -0.1700
Data Index: 7355366 (The Pile)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.7330. Min Act: -0.1700
Data Index: 6664965 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6851. Min Act: -0.1700
Data Index: 546924 (The Pile)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6690. Min Act: -0.1700
Data Index: 6035450 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6851. Min Act: -0.1700
Data Index: 7744219 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6530. Min Act: -0.1700
Data Index: 5395735 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6530. Min Act: -0.1700
Data Index: 9052976 (The Pile)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6530. Min Act: -0.1700
Data Index: 7475773 (The Pile)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6530. Min Act: -0.1700
Data Index: 6264289 (The Pile)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6369. Min Act: -0.1700
Data Index: 3000530 (The Pile)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6530. Min Act: -0.1700
Data Index: 4772281 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6048. Min Act: -0.1700
Data Index: 7254407 (The Pile)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6209. Min Act: -0.1700
Data Index: 5219254 (The Pile)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6369. Min Act: -0.1700
Data Index: 1198671 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6369. Min Act: -0.1700
Data Index: 4778038 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6209. Min Act: -0.1700
Data Index: 1501718 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6048. Min Act: -0.1700
Data Index: 4976564 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6048. Min Act: -0.1700
Data Index: 3285550 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6209. Min Act: -0.1700
Data Index: 6789138 (The Pile)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7968. Min Range: -2.7968
Max Act: 2.6048. Min Act: -0.1700
Data Index: 8885529 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19