Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 774 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.6213. Min Act: -0.0000

Data Index: 684848 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.2997. Min Act: -0.0000

Data Index: 51884 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.2919. Min Act: -0.0000

Data Index: 226733 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.2024. Min Act: -0.0000

Data Index: 1165224 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.3122. Min Act: -0.0000

Data Index: 1003799 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.3187. Min Act: -0.0000

Data Index: 730437 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.2068. Min Act: -0.0000

Data Index: 432463 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.3962. Min Act: -0.0000

Data Index: 520749 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.2829. Min Act: -0.0000

Data Index: 254140 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.1358. Min Act: -0.0000

Data Index: 1033410 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.0139. Min Act: -0.0000

Data Index: 1126405 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.1190. Min Act: -0.0000

Data Index: 574766 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.1183. Min Act: -0.0000

Data Index: 1133976 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.0085. Min Act: -0.0000

Data Index: 987201 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.0079. Min Act: -0.0000

Data Index: 296754 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 2.6213. Min Range: -2.6213

Max Act: 1.9760. Min Act: -0.0000

Data Index: 1350114 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 2.6213. Min Range: -2.6213

Max Act: 1.8485. Min Act: -0.0000

Data Index: 349161 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 2.6213. Min Range: -2.6213

Max Act: 1.9382. Min Act: -0.0000

Data Index: 1087859 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 2.6213. Min Range: -2.6213

Max Act: 1.9510. Min Act: -0.0000

Data Index: 674033 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 2.6213. Min Range: -2.6213

Max Act: 2.0336. Min Act: -0.0000

Data Index: 708887 (C4 (Web Text))

Max Activating Token Index: 334