Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3832 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.5247. Min Act: -0.0001
Data Index: 816907 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.3938. Min Act: -0.0001
Data Index: 116197 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4038. Min Act: -0.0001
Data Index: 1332133 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.3674. Min Act: -0.0001
Data Index: 588222 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.2929. Min Act: -0.0001
Data Index: 662648 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.2441. Min Act: -0.0001
Data Index: 1061429 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.2632. Min Act: -0.0001
Data Index: 403315 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.1077. Min Act: -0.0001
Data Index: 934924 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.1527. Min Act: -0.0001
Data Index: 710920 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.1846. Min Act: -0.0001
Data Index: 1109878 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.1539. Min Act: -0.0001
Data Index: 995521 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.2154. Min Act: -0.0001
Data Index: 1110656 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.1580. Min Act: -0.0001
Data Index: 1023342 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.1489. Min Act: -0.0001
Data Index: 861538 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.1656. Min Act: -0.0001
Data Index: 99850 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.1577. Min Act: -0.0001
Data Index: 446592 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.1596. Min Act: -0.0001
Data Index: 71183 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.0853. Min Act: -0.0001
Data Index: 1015276 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.0819. Min Act: -0.0001
Data Index: 295511 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.0248. Min Act: -0.0001
Data Index: 1258455 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19