Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1338 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.2990. Min Range: -1.2990
Max Act: 1.2990. Min Act: -0.0000
Data Index: 1006981 (The Pile)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.9907. Min Act: -0.0000
Data Index: 116980 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.9423. Min Act: -0.0000
Data Index: 101475 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2990. Min Range: -1.2990
Max Act: 1.0623. Min Act: 0.0002
Data Index: 368608 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.9564. Min Act: -0.0000
Data Index: 1808937 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.9355. Min Act: 0.0001
Data Index: 515540 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.9130. Min Act: -0.0000
Data Index: 567736 (The Pile)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.9221. Min Act: -0.0000
Data Index: 1253877 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.9192. Min Act: 0.0000
Data Index: 1970348 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.9004. Min Act: 0.0000
Data Index: 1433675 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.8369. Min Act: -0.0000
Data Index: 201939 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.8490. Min Act: -0.0000
Data Index: 1976113 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.8278. Min Act: -0.0000
Data Index: 1380207 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.8667. Min Act: -0.0000
Data Index: 232489 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.8615. Min Act: -0.0000
Data Index: 1578956 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.8584. Min Act: -0.0000
Data Index: 334467 (The Pile)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.8193. Min Act: -0.0000
Data Index: 1569164 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.8304. Min Act: 0.0000
Data Index: 1758554 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.8558. Min Act: -0.0000
Data Index: 810222 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2990. Min Range: -1.2990
Max Act: 0.8719. Min Act: -0.0000
Data Index: 1175421 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19