Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 36 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.1334. Min Range: -2.1334
Max Act: 2.1334. Min Act: -0.0001
Data Index: 1118921 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1334. Min Range: -2.1334
Max Act: 2.0225. Min Act: -0.0001
Data Index: 327817 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.7967. Min Act: -0.0001
Data Index: 1047560 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.7780. Min Act: -0.0001
Data Index: 760330 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.7639. Min Act: -0.0001
Data Index: 1136162 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.6464. Min Act: -0.0001
Data Index: 1114053 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.7264. Min Act: -0.0001
Data Index: 189044 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.6106. Min Act: -0.0001
Data Index: 1052879 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.7449. Min Act: -0.0001
Data Index: 724179 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.5640. Min Act: -0.0001
Data Index: 293281 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.5142. Min Act: -0.0001
Data Index: 327792 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.6973. Min Act: -0.0001
Data Index: 19929 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.5243. Min Act: -0.0001
Data Index: 1057916 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.5476. Min Act: -0.0001
Data Index: 467174 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.5716. Min Act: -0.0001
Data Index: 1055010 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.5188. Min Act: -0.0001
Data Index: 1331224 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.5171. Min Act: -0.0001
Data Index: 582120 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.5104. Min Act: -0.0001
Data Index: 48730 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.5507. Min Act: -0.0001
Data Index: 62658 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1334. Min Range: -2.1334
Max Act: 1.4790. Min Act: -0.0001
Data Index: 632494 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19