Model: None
Dataset: The Pile
Neuron 794 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.7798. Min Act: -0.1700
Data Index: 8084271 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.7798. Min Act: -0.1700
Data Index: 2598612 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.7638. Min Act: -0.1700
Data Index: 10623276 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.7319. Min Act: -0.1700
Data Index: 2168165 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6999. Min Act: -0.1700
Data Index: 7336899 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6999. Min Act: -0.1700
Data Index: 7976788 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6839. Min Act: -0.1700
Data Index: 5654537 (The Pile)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.7159. Min Act: -0.1700
Data Index: 7038778 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.7319. Min Act: -0.1700
Data Index: 3207824 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.7159. Min Act: -0.1700
Data Index: 8182453 (The Pile)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6839. Min Act: -0.1700
Data Index: 5438131 (The Pile)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6839. Min Act: -0.1700
Data Index: 8206506 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.7159. Min Act: -0.1700
Data Index: 8865050 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6839. Min Act: -0.1700
Data Index: 5419237 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6999. Min Act: -0.1700
Data Index: 8283268 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6839. Min Act: -0.1700
Data Index: 4974369 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.7159. Min Act: -0.1700
Data Index: 4611170 (The Pile)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6839. Min Act: -0.1700
Data Index: 4252391 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6839. Min Act: -0.1700
Data Index: 5242586 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7798. Min Range: -2.7798
Max Act: 2.6839. Min Act: -0.1700
Data Index: 10215688 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19