Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 995 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.2319. Min Range: -2.2319
Max Act: 2.0089. Min Act: -0.0001
Data Index: 1971020 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2319. Min Range: -2.2319
Max Act: 2.0828. Min Act: -0.0001
Data Index: 331115 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2319. Min Range: -2.2319
Max Act: 2.2319. Min Act: -0.0001
Data Index: 189896 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2319. Min Range: -2.2319
Max Act: 2.1858. Min Act: -0.0001
Data Index: 1772748 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2319. Min Range: -2.2319
Max Act: 2.0928. Min Act: -0.0001
Data Index: 418799 (The Pile)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2319. Min Range: -2.2319
Max Act: 2.0592. Min Act: -0.0001
Data Index: 649249 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2319. Min Range: -2.2319
Max Act: 1.8472. Min Act: -0.0001
Data Index: 1856685 (The Pile)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2319. Min Range: -2.2319
Max Act: 2.0461. Min Act: -0.0001
Data Index: 1646396 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2319. Min Range: -2.2319
Max Act: 2.0497. Min Act: -0.0001
Data Index: 1380636 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2319. Min Range: -2.2319
Max Act: 2.0569. Min Act: -0.0001
Data Index: 1342027 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2319. Min Range: -2.2319
Max Act: 1.9249. Min Act: -0.0001
Data Index: 473959 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2319. Min Range: -2.2319
Max Act: 1.8856. Min Act: -0.0001
Data Index: 952326 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2319. Min Range: -2.2319
Max Act: 1.7269. Min Act: -0.0001
Data Index: 536769 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2319. Min Range: -2.2319
Max Act: 2.0435. Min Act: -0.0001
Data Index: 1746940 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2319. Min Range: -2.2319
Max Act: 1.9358. Min Act: -0.0001
Data Index: 897800 (The Pile)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2319. Min Range: -2.2319
Max Act: 1.7588. Min Act: -0.0001
Data Index: 419006 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2319. Min Range: -2.2319
Max Act: 1.7212. Min Act: -0.0001
Data Index: 1683753 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2319. Min Range: -2.2319
Max Act: 1.8417. Min Act: -0.0001
Data Index: 1652577 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2319. Min Range: -2.2319
Max Act: 1.5194. Min Act: -0.0001
Data Index: 1456271 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2319. Min Range: -2.2319
Max Act: 1.8093. Min Act: -0.0001
Data Index: 1968594 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19