Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 540 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.8384. Min Act: -0.0001
Data Index: 589467 (The Pile)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6889. Min Act: -0.0001
Data Index: 91599 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6811. Min Act: -0.0001
Data Index: 1195428 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6050. Min Act: -0.0001
Data Index: 1796508 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6446. Min Act: -0.0001
Data Index: 843378 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.5570. Min Act: -0.0001
Data Index: 1783316 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.5963. Min Act: -0.0001
Data Index: 498229 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6210. Min Act: -0.0001
Data Index: 1638256 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6220. Min Act: -0.0001
Data Index: 787269 (The Pile)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.5761. Min Act: -0.0001
Data Index: 1192632 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6397. Min Act: -0.0001
Data Index: 741692 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6183. Min Act: -0.0001
Data Index: 1637708 (The Pile)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6179. Min Act: -0.0001
Data Index: 429536 (The Pile)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.5760. Min Act: -0.0001
Data Index: 1778912 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.5961. Min Act: -0.0001
Data Index: 1457194 (The Pile)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6008. Min Act: -0.0001
Data Index: 137795 (The Pile)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.5709. Min Act: -0.0001
Data Index: 1586384 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.5781. Min Act: -0.0001
Data Index: 1248172 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6523. Min Act: -0.0001
Data Index: 1237588 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8384. Min Range: -0.8384
Max Act: 0.6205. Min Act: -0.0001
Data Index: 34090 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19