Model: None
Dataset: The Pile
Neuron 3872 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.6645. Min Act: -0.1700
Data Index: 4356896 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.6488. Min Act: -0.1700
Data Index: 436884 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.6332. Min Act: -0.1700
Data Index: 8216537 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.6332. Min Act: -0.1700
Data Index: 10197153 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.6175. Min Act: -0.1700
Data Index: 2655799 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.6175. Min Act: -0.1700
Data Index: 1605797 (The Pile)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.6175. Min Act: -0.1700
Data Index: 7613040 (The Pile)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.6175. Min Act: -0.1700
Data Index: 4077124 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5862. Min Act: -0.1700
Data Index: 4145387 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5862. Min Act: -0.1700
Data Index: 8720343 (The Pile)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5862. Min Act: -0.1700
Data Index: 5614279 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5705. Min Act: -0.1700
Data Index: 4808517 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5549. Min Act: -0.1700
Data Index: 6265632 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5549. Min Act: -0.1700
Data Index: 1006383 (The Pile)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5549. Min Act: -0.1700
Data Index: 356626 (The Pile)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5392. Min Act: -0.1700
Data Index: 9109404 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5392. Min Act: -0.1700
Data Index: 1487642 (The Pile)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5235. Min Act: -0.1700
Data Index: 1737182 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5079. Min Act: -0.1700
Data Index: 769475 (The Pile)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6645. Min Range: -3.6645
Max Act: 3.5079. Min Act: -0.1700
Data Index: 8868023 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19