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

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

Neuron 1902 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2493. Min Act: -0.0000

Data Index: 234952 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2423. Min Act: -0.0001

Data Index: 582042 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2445. Min Act: -0.0001

Data Index: 690335 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2312. Min Act: -0.0001

Data Index: 1246202 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2185. Min Act: -0.0001

Data Index: 307742 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2182. Min Act: -0.0001

Data Index: 857154 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1035336 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2195. Min Act: -0.0001

Data Index: 987854 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2183. Min Act: -0.0001

Data Index: 825861 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2179. Min Act: -0.0001

Data Index: 169607 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2063. Min Act: -0.0001

Data Index: 1154125 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1057061 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2015. Min Act: -0.0001

Data Index: 567266 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2021. Min Act: -0.0000

Data Index: 568188 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2053. Min Act: -0.0001

Data Index: 1226340 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2055. Min Act: -0.0001

Data Index: 524482 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2034. Min Act: -0.0001

Data Index: 863204 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1991. Min Act: -0.0001

Data Index: 875837 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2023. Min Act: -0.0001

Data Index: 661441 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1932. Min Act: -0.0001

Data Index: 650841 (C4 (Web Text))

Max Activating Token Index: 926