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

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

Neuron 5286 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2675. Min Act: -0.0000

Data Index: 32811 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2411. Min Act: -0.0000

Data Index: 353118 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2530. Min Act: -0.0000

Data Index: 177273 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1028686 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2312. Min Act: -0.0000

Data Index: 199437 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2072. Min Act: -0.0000

Data Index: 474166 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2121. Min Act: -0.0000

Data Index: 62428 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2064. Min Act: -0.0000

Data Index: 574152 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.1993. Min Act: -0.0000

Data Index: 580970 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2028. Min Act: -0.0000

Data Index: 401613 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2171. Min Act: -0.0000

Data Index: 289384 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2050. Min Act: -0.0000

Data Index: 394056 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2224. Min Act: -0.0000

Data Index: 51931 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1329976 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2033. Min Act: -0.0000

Data Index: 156361 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2027. Min Act: -0.0000

Data Index: 382054 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1307327 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2065. Min Act: -0.0000

Data Index: 757825 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2103. Min Act: -0.0000

Data Index: 161732 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2022. Min Act: -0.0000

Data Index: 987769 (C4 (Web Text))

Max Activating Token Index: 84