Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 414 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.1163. Min Range: -3.1163
Max Act: 3.1163. Min Act: -0.0001
Data Index: 666332 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1163. Min Range: -3.1163
Max Act: 2.6051. Min Act: -0.0001
Data Index: 49974 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1163. Min Range: -3.1163
Max Act: 2.3412. Min Act: -0.0001
Data Index: 45153 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1163. Min Range: -3.1163
Max Act: 2.3131. Min Act: -0.0001
Data Index: 633731 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1163. Min Range: -3.1163
Max Act: 2.1667. Min Act: -0.0001
Data Index: 226052 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1163. Min Range: -3.1163
Max Act: 2.1547. Min Act: -0.0001
Data Index: 253273 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1163. Min Range: -3.1163
Max Act: 2.1566. Min Act: -0.0001
Data Index: 772892 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1163. Min Range: -3.1163
Max Act: 2.5669. Min Act: -0.0001
Data Index: 448221 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1163. Min Range: -3.1163
Max Act: 2.0325. Min Act: -0.0001
Data Index: 739501 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1163. Min Range: -3.1163
Max Act: 2.1529. Min Act: -0.0001
Data Index: 78382 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1163. Min Range: -3.1163
Max Act: 2.0082. Min Act: -0.0001
Data Index: 441457 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1163. Min Range: -3.1163
Max Act: 1.9892. Min Act: -0.0001
Data Index: 1053991 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1163. Min Range: -3.1163
Max Act: 1.9587. Min Act: -0.0001
Data Index: 306401 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1163. Min Range: -3.1163
Max Act: 1.5093. Min Act: -0.0001
Data Index: 733553 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1163. Min Range: -3.1163
Max Act: 1.9412. Min Act: -0.0001
Data Index: 479320 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1163. Min Range: -3.1163
Max Act: 1.8159. Min Act: -0.0001
Data Index: 174263 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1163. Min Range: -3.1163
Max Act: 1.8109. Min Act: -0.0001
Data Index: 1089706 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1163. Min Range: -3.1163
Max Act: 1.8031. Min Act: -0.0001
Data Index: 1028720 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1163. Min Range: -3.1163
Max Act: 1.8626. Min Act: -0.0001
Data Index: 600988 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1163. Min Range: -3.1163
Max Act: 1.9244. Min Act: -0.0001
Data Index: 698942 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19