Model: None
Dataset: The Pile
Neuron 2009 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.8479. Min Act: -0.1700
Data Index: 5371606 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.8320. Min Act: -0.1700
Data Index: 3922084 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.8161. Min Act: -0.1700
Data Index: 2873317 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.8002. Min Act: -0.1700
Data Index: 9630835 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7843. Min Act: -0.1700
Data Index: 5795369 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7683. Min Act: -0.1700
Data Index: 6895033 (The Pile)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7843. Min Act: -0.1700
Data Index: 6799177 (The Pile)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7843. Min Act: -0.1700
Data Index: 9719832 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7364. Min Act: -0.1700
Data Index: 5826647 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7683. Min Act: -0.1700
Data Index: 6777919 (The Pile)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7364. Min Act: -0.1700
Data Index: 8907939 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7683. Min Act: -0.1700
Data Index: 3369588 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7683. Min Act: -0.1700
Data Index: 169916 (The Pile)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7683. Min Act: -0.1700
Data Index: 7545449 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7683. Min Act: -0.1700
Data Index: 3963213 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7524. Min Act: -0.1700
Data Index: 9625992 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7524. Min Act: -0.1700
Data Index: 2500852 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7524. Min Act: -0.1700
Data Index: 8881994 (The Pile)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7364. Min Act: -0.1700
Data Index: 108200 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7364. Min Act: -0.1700
Data Index: 2335649 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19