Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1469 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.8171. Min Act: -0.0002
Data Index: 1222139 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.8656. Min Act: -0.0001
Data Index: 819647 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.8166. Min Act: -0.0002
Data Index: 548449 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.4976. Min Act: -0.0001
Data Index: 173913 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.5456. Min Act: -0.0002
Data Index: 112964 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.6479. Min Act: -0.0002
Data Index: 174459 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.4186. Min Act: -0.0002
Data Index: 868239 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.4382. Min Act: -0.0001
Data Index: 991200 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.3500. Min Act: -0.0001
Data Index: 342844 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.5535. Min Act: -0.0002
Data Index: 1033333 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.3533. Min Act: -0.0001
Data Index: 534522 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.2704. Min Act: -0.0001
Data Index: 219232 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.4006. Min Act: -0.0001
Data Index: 930020 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.3666. Min Act: -0.0001
Data Index: 17288 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.3143. Min Act: -0.0002
Data Index: 298900 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.2318. Min Act: -0.0001
Data Index: 501541 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.3684. Min Act: -0.0001
Data Index: 305620 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.4088. Min Act: -0.0002
Data Index: 38366 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.2780. Min Act: -0.0002
Data Index: 1286527 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8656. Min Range: -2.8656
Max Act: 2.1634. Min Act: -0.0002
Data Index: 1216961 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19