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

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

Neuron 4485 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1979. Min Range: -1.1979

Max Act: 1.1979. Min Act: -0.0000

Data Index: 1039737 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 1.1979. Min Range: -1.1979

Max Act: 1.0703. Min Act: -0.0000

Data Index: 692754 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 1.1979. Min Range: -1.1979

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1041049 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 1.1979. Min Range: -1.1979

Max Act: 1.1540. Min Act: -0.0001

Data Index: 1373592 (Python Code)

Max Activating Token Index: 852

Text #4

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.9819. Min Act: -0.0001

Data Index: 272755 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 1.1979. Min Range: -1.1979

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1148897 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.1979. Min Range: -1.1979

Max Act: 1.0176. Min Act: -0.0001

Data Index: 575270 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 1.1979. Min Range: -1.1979

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1239225 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.8953. Min Act: -0.0000

Data Index: 1032323 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1075411 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.9204. Min Act: -0.0000

Data Index: 771429 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.9610. Min Act: -0.0000

Data Index: 489498 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.1979. Min Range: -1.1979

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1306904 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1194228 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.9299. Min Act: -0.0000

Data Index: 137089 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1209721 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.9428. Min Act: -0.0000

Data Index: 541765 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.9250. Min Act: -0.0000

Data Index: 831965 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.8903. Min Act: -0.0000

Data Index: 345232 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 1.1979. Min Range: -1.1979

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1302523 (C4 (Web Text))

Max Activating Token Index: 957