Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 969 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.5077. Min Act: -0.0002

Data Index: 1016709 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4460. Min Act: -0.0003

Data Index: 949579 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3681. Min Act: -0.0002

Data Index: 526183 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3470. Min Act: -0.0002

Data Index: 268895 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3481. Min Act: -0.0002

Data Index: 985905 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3450. Min Act: -0.0002

Data Index: 79071 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3391. Min Act: 0.0000

Data Index: 1539658 (Python Code)

Max Activating Token Index: 851

Text #7

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3343. Min Act: -0.0002

Data Index: 1325295 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3305. Min Act: -0.0002

Data Index: 1259000 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3404. Min Act: -0.0003

Data Index: 1411452 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3296. Min Act: -0.0002

Data Index: 928556 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3299. Min Act: -0.0003

Data Index: 1423289 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3245. Min Act: -0.0002

Data Index: 1651545 (Python Code)

Max Activating Token Index: 339

Text #13

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3229. Min Act: -0.0002

Data Index: 457565 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3213. Min Act: -0.0002

Data Index: 54409 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3206. Min Act: -0.0003

Data Index: 1376365 (Python Code)

Max Activating Token Index: 788

Text #16

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3151. Min Act: -0.0002

Data Index: 1371050 (Python Code)

Max Activating Token Index: 400

Text #17

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3133. Min Act: -0.0002

Data Index: 1240504 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3125. Min Act: -0.0002

Data Index: 1231642 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3105. Min Act: -0.0003

Data Index: 1380734 (Python Code)

Max Activating Token Index: 109