Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1785 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0002

Data Index: 389455 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1065134 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0332. Min Act: -0.0002

Data Index: 2540 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0272. Min Act: -0.0002

Data Index: 21792 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1331942 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0242. Min Act: -0.0002

Data Index: 201283 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1152948 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1028125 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1275986 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0249. Min Act: -0.0002

Data Index: 442013 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1302643 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1224969 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0233. Min Act: -0.0002

Data Index: 491552 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0240. Min Act: -0.0002

Data Index: 72352 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0228. Min Act: -0.0002

Data Index: 450120 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0234. Min Act: -0.0002

Data Index: 749039 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1004181 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0241. Min Act: -0.0002

Data Index: 156726 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0237. Min Act: -0.0002

Data Index: 543171 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1307485 (C4 (Web Text))

Max Activating Token Index: 498