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

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

Neuron 16 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: 3.5968. Min Range: -3.5968

Max Act: 3.5968. Min Act: -0.0000

Data Index: 307369 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.5803. Min Act: -0.0000

Data Index: 1618324 (Python Code)

Max Activating Token Index: 82

Text #2

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.1167. Min Act: -0.0000

Data Index: 600338 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.3872. Min Act: -0.0000

Data Index: 1107984 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.2211. Min Act: -0.0000

Data Index: 1428467 (Python Code)

Max Activating Token Index: 346

Text #5

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.3744. Min Act: -0.0000

Data Index: 146566 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.2187. Min Act: -0.0000

Data Index: 1503459 (Python Code)

Max Activating Token Index: 902

Text #7

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.2530. Min Act: -0.0000

Data Index: 1566246 (Python Code)

Max Activating Token Index: 180

Text #8

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.4262. Min Act: -0.0000

Data Index: 823084 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.1366. Min Act: -0.0000

Data Index: 1619309 (Python Code)

Max Activating Token Index: 894

Text #10

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.8244. Min Act: -0.0000

Data Index: 977003 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.0439. Min Act: -0.0000

Data Index: 1626412 (Python Code)

Max Activating Token Index: 691

Text #12

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.0369. Min Act: -0.0000

Data Index: 1496214 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.0150. Min Act: -0.0000

Data Index: 295825 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.7034. Min Act: -0.0000

Data Index: 534596 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.9917. Min Act: -0.0000

Data Index: 1373553 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.1250. Min Act: -0.0000

Data Index: 1571752 (Python Code)

Max Activating Token Index: 218

Text #17

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.1369. Min Act: -0.0000

Data Index: 928726 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.0867. Min Act: -0.0000

Data Index: 1070551 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.8906. Min Act: -0.0000

Data Index: 1558257 (Python Code)

Max Activating Token Index: 833