Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2066 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.4238. Min Act: -0.0001

Data Index: 1588639 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.3174. Min Act: -0.0001

Data Index: 638936 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.3220. Min Act: -0.0001

Data Index: 34531 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.2708. Min Act: -0.0001

Data Index: 250175 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.3035. Min Act: -0.0001

Data Index: 1289533 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.2897. Min Act: -0.0001

Data Index: 861317 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1987. Min Act: -0.0001

Data Index: 1130470 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.2277. Min Act: -0.0001

Data Index: 681928 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1414. Min Act: -0.0001

Data Index: 716092 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1028. Min Act: -0.0001

Data Index: 455333 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1703. Min Act: -0.0001

Data Index: 376695 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1610. Min Act: -0.0001

Data Index: 146719 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1891. Min Act: -0.0001

Data Index: 950421 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1847. Min Act: -0.0001

Data Index: 1077908 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0239. Min Act: -0.0001

Data Index: 338905 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0731. Min Act: -0.0001

Data Index: 520937 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0710. Min Act: -0.0001

Data Index: 763586 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1250. Min Act: -0.0001

Data Index: 120689 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0876. Min Act: -0.0001

Data Index: 174619 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0486. Min Act: -0.0001

Data Index: 1208326 (C4 (Web Text))

Max Activating Token Index: 943