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

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

Neuron 2056 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0002

Data Index: 50088 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0183. Min Act: -0.0002

Data Index: 211902 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0191. Min Act: -0.0002

Data Index: 350761 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0184. Min Act: -0.0002

Data Index: 689885 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0181. Min Act: -0.0002

Data Index: 84024 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0177. Min Act: -0.0002

Data Index: 858401 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0178. Min Act: -0.0002

Data Index: 251187 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0171. Min Act: -0.0002

Data Index: 303192 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1740 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0171. Min Act: -0.0002

Data Index: 749711 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1320988 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0167. Min Act: -0.0002

Data Index: 412001 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1113958 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0163. Min Act: -0.0002

Data Index: 824420 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0162. Min Act: -0.0002

Data Index: 779649 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0161. Min Act: -0.0002

Data Index: 311761 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0154. Min Act: -0.0002

Data Index: 277922 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0157. Min Act: -0.0002

Data Index: 810234 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1025724 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0162. Min Act: -0.0002

Data Index: 116058 (C4 (Web Text))

Max Activating Token Index: 470