Model: None
Dataset: The Pile
Neuron 782 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.8651. Min Act: -0.1700
Data Index: 2281414 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.7377. Min Act: -0.1700
Data Index: 10409073 (The Pile)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6897. Min Act: -0.1700
Data Index: 4119085 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6897. Min Act: -0.1700
Data Index: 7321228 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6416. Min Act: -0.1700
Data Index: 4644212 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6897. Min Act: -0.1700
Data Index: 3722995 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6095. Min Act: -0.1700
Data Index: 1740268 (The Pile)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6576. Min Act: -0.1700
Data Index: 10656932 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6416. Min Act: -0.1700
Data Index: 7702702 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.5773. Min Act: -0.1700
Data Index: 8372650 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.5934. Min Act: -0.1700
Data Index: 5296759 (The Pile)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6416. Min Act: -0.1700
Data Index: 2212055 (The Pile)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6095. Min Act: -0.1700
Data Index: 6370637 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.5934. Min Act: -0.1700
Data Index: 1343940 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6095. Min Act: -0.1700
Data Index: 10569402 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.5934. Min Act: -0.1700
Data Index: 1026399 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.6095. Min Act: -0.1700
Data Index: 1991495 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.5773. Min Act: -0.1700
Data Index: 3562891 (The Pile)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.5611. Min Act: -0.1700
Data Index: 7310423 (The Pile)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8651. Min Range: -2.8651
Max Act: 2.5450. Min Act: -0.1700
Data Index: 7105034 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19