Model: None
Dataset: The Pile
Neuron 1193 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.5514. Min Act: -0.1700
Data Index: 4614122 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.5514. Min Act: -0.1700
Data Index: 6096204 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.5514. Min Act: -0.1700
Data Index: 2835484 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.5357. Min Act: -0.1700
Data Index: 1764969 (The Pile)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.5357. Min Act: -0.1700
Data Index: 1990439 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.5357. Min Act: -0.1700
Data Index: 3893234 (The Pile)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.5357. Min Act: -0.1700
Data Index: 8271007 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.5200. Min Act: -0.1700
Data Index: 5858113 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.4730. Min Act: -0.1700
Data Index: 10648259 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.4260. Min Act: -0.1700
Data Index: 10713647 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.4103. Min Act: -0.1700
Data Index: 7282107 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.3946. Min Act: -0.1700
Data Index: 65820 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.3790. Min Act: -0.1700
Data Index: 9947233 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.3790. Min Act: -0.1700
Data Index: 4186373 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.3319. Min Act: -0.1700
Data Index: 6070978 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.3319. Min Act: -0.1700
Data Index: 7620119 (The Pile)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.3005. Min Act: -0.1700
Data Index: 6169389 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.3005. Min Act: -0.1700
Data Index: 3981463 (The Pile)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.3005. Min Act: -0.1700
Data Index: 2301029 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5514. Min Range: -3.5514
Max Act: 3.3005. Min Act: -0.1700
Data Index: 2109066 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19