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

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

Neuron 172 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.5158. Min Act: -0.0000

Data Index: 446720 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3710. Min Act: -0.0000

Data Index: 232137 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1130532 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3235. Min Act: -0.0000

Data Index: 588638 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3374. Min Act: -0.0000

Data Index: 139816 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1082942 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3232. Min Act: -0.0000

Data Index: 608674 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1013923 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1083107 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1095496 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.2983. Min Act: -0.0000

Data Index: 875693 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1045061 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.2742. Min Act: -0.0000

Data Index: 647324 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.2710. Min Act: -0.0000

Data Index: 58564 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.2525. Min Act: 0.0000

Data Index: 488461 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.2446. Min Act: -0.0000

Data Index: 86485 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.2281. Min Act: -0.0000

Data Index: 909164 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.2273. Min Act: -0.0000

Data Index: 503778 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.2250. Min Act: -0.0000

Data Index: 289938 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1254145 (C4 (Web Text))

Max Activating Token Index: 911