Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 809 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1440. Min Range: -2.1440

Max Act: 2.1440. Min Act: -0.0000

Data Index: 455391 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 2.1440. Min Range: -2.1440

Max Act: 2.1160. Min Act: -0.0000

Data Index: 1172854 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.9801. Min Act: -0.0000

Data Index: 1070351 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.8318. Min Act: -0.0000

Data Index: 800499 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.8031. Min Act: -0.0000

Data Index: 784576 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.8014. Min Act: 0.0000

Data Index: 545233 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.7350. Min Act: -0.0000

Data Index: 782020 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.5597. Min Act: -0.0000

Data Index: 908757 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.7431. Min Act: -0.0000

Data Index: 1138791 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.6324. Min Act: -0.0000

Data Index: 870316 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.7299. Min Act: -0.0000

Data Index: 1075657 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.7179. Min Act: -0.0000

Data Index: 1340148 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.5238. Min Act: -0.0000

Data Index: 370381 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.6188. Min Act: -0.0000

Data Index: 827782 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.6038. Min Act: -0.0000

Data Index: 1290440 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.5957. Min Act: -0.0000

Data Index: 343964 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.6034. Min Act: -0.0000

Data Index: 515935 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.5937. Min Act: -0.0000

Data Index: 735765 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.4765. Min Act: -0.0000

Data Index: 266085 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 2.1440. Min Range: -2.1440

Max Act: 1.6461. Min Act: -0.0000

Data Index: 1069870 (C4 (Web Text))

Max Activating Token Index: 566