Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2435 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.6990. Min Act: -0.0001
Data Index: 1712472 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.6229. Min Act: -0.0001
Data Index: 1049210 (The Pile)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.6438. Min Act: -0.0001
Data Index: 944603 (The Pile)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.6339. Min Act: -0.0001
Data Index: 1695809 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5887. Min Act: -0.0001
Data Index: 1727403 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5615. Min Act: -0.0001
Data Index: 844621 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5630. Min Act: -0.0001
Data Index: 1847486 (The Pile)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5566. Min Act: -0.0001
Data Index: 500496 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5223. Min Act: -0.0001
Data Index: 527856 (The Pile)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5045. Min Act: -0.0001
Data Index: 199319 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5358. Min Act: -0.0001
Data Index: 157784 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5288. Min Act: -0.0001
Data Index: 373836 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5204. Min Act: -0.0001
Data Index: 778583 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5166. Min Act: -0.0001
Data Index: 864373 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5176. Min Act: -0.0001
Data Index: 1301502 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.4985. Min Act: -0.0001
Data Index: 474997 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5143. Min Act: -0.0001
Data Index: 419331 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.5297. Min Act: -0.0001
Data Index: 1224881 (The Pile)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.4872. Min Act: -0.0001
Data Index: 478930 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6990. Min Range: -0.6990
Max Act: 0.4917. Min Act: -0.0001
Data Index: 1459507 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19