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

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

Neuron 3065 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.7962. Min Act: -0.0000

Data Index: 706427 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.5570. Min Act: -0.0000

Data Index: 186684 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.6726. Min Act: -0.0000

Data Index: 120201 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.5173. Min Act: -0.0000

Data Index: 152340 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.5225. Min Act: -0.0000

Data Index: 129040 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.3248. Min Act: -0.0000

Data Index: 1305664 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.4290. Min Act: -0.0000

Data Index: 70647 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.5335. Min Act: -0.0000

Data Index: 62873 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.2939. Min Act: -0.0000

Data Index: 333762 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.5344. Min Act: -0.0000

Data Index: 851084 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.3157. Min Act: -0.0000

Data Index: 790383 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.3970. Min Act: -0.0000

Data Index: 721045 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.2631. Min Act: -0.0000

Data Index: 938236 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.3883. Min Act: -0.0000

Data Index: 644487 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.3833. Min Act: -0.0000

Data Index: 1262173 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.3897. Min Act: -0.0000

Data Index: 129522 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.2297. Min Act: -0.0000

Data Index: 1159418 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.3715. Min Act: -0.0000

Data Index: 1336336 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.2069. Min Act: -0.0000

Data Index: 1023876 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 2.7962. Min Range: -2.7962

Max Act: 2.2359. Min Act: -0.0000

Data Index: 124366 (C4 (Web Text))

Max Activating Token Index: 897