Model: None
Dataset: The Pile
Neuron 856 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.3732. Min Act: -0.1700
Data Index: 7916768 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.3575. Min Act: -0.1700
Data Index: 9673585 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.3418. Min Act: -0.1700
Data Index: 1188343 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2947. Min Act: -0.1700
Data Index: 5075022 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2947. Min Act: -0.1700
Data Index: 3492005 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2790. Min Act: -0.1700
Data Index: 3736207 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2790. Min Act: -0.1700
Data Index: 466157 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2790. Min Act: -0.1700
Data Index: 4532511 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2632. Min Act: -0.1700
Data Index: 4751662 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2632. Min Act: -0.1700
Data Index: 9299866 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2632. Min Act: -0.1700
Data Index: 10110740 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2475. Min Act: -0.1700
Data Index: 3063445 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2475. Min Act: -0.1700
Data Index: 601075 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2475. Min Act: -0.1700
Data Index: 7141375 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2475. Min Act: -0.1700
Data Index: 2277590 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2475. Min Act: -0.1700
Data Index: 1614938 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2318. Min Act: -0.1700
Data Index: 7055277 (The Pile)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2318. Min Act: -0.1700
Data Index: 4162200 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2318. Min Act: -0.1700
Data Index: 5102184 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3732. Min Range: -3.3732
Max Act: 3.2318. Min Act: -0.1700
Data Index: 4985435 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19