Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1798 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2661. Min Act: -0.0001
Data Index: 1294439 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2533. Min Act: -0.0001
Data Index: 141483 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2652. Min Act: -0.0001
Data Index: 1004397 (The Pile)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2517. Min Act: -0.0001
Data Index: 267432 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2389. Min Act: -0.0001
Data Index: 564831 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2476. Min Act: -0.0001
Data Index: 1486405 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2760. Min Act: -0.0001
Data Index: 24790 (The Pile)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2437. Min Act: -0.0001
Data Index: 483678 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2697. Min Act: -0.0001
Data Index: 1531915 (The Pile)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2177. Min Act: -0.0001
Data Index: 604786 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2244. Min Act: -0.0001
Data Index: 286327 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2594. Min Act: -0.0001
Data Index: 1839520 (The Pile)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2271. Min Act: -0.0001
Data Index: 382746 (The Pile)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2194. Min Act: -0.0001
Data Index: 1247483 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2575. Min Act: -0.0001
Data Index: 145949 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2644. Min Act: -0.0001
Data Index: 1918182 (The Pile)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2424. Min Act: -0.0001
Data Index: 1266789 (The Pile)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2273. Min Act: -0.0001
Data Index: 612371 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2326. Min Act: -0.0001
Data Index: 1034478 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2760. Min Range: -0.2760
Max Act: 0.2546. Min Act: -0.0001
Data Index: 234952 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19