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

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

Neuron 305 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1942. Min Range: -1.1942

Max Act: 1.1942. Min Act: -0.0000

Data Index: 991954 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 1.1942. Min Range: -1.1942

Max Act: 1.0779. Min Act: -0.0000

Data Index: 460092 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9792. Min Act: -0.0000

Data Index: 41753 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 1.1942. Min Range: -1.1942

Max Act: 1.0305. Min Act: -0.0000

Data Index: 671866 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9751. Min Act: -0.0000

Data Index: 471589 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1058599 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9179. Min Act: -0.0000

Data Index: 508260 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 1.1942. Min Range: -1.1942

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1281101 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9118. Min Act: -0.0000

Data Index: 375458 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9636. Min Act: -0.0000

Data Index: 322120 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9550. Min Act: -0.0000

Data Index: 423262 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 1.1942. Min Range: -1.1942

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1316359 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9582. Min Act: -0.0000

Data Index: 550218 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9787. Min Act: -0.0000

Data Index: 240287 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9279. Min Act: -0.0000

Data Index: 356203 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8921. Min Act: -0.0000

Data Index: 517564 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1181338 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9044. Min Act: -0.0000

Data Index: 298462 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9271. Min Act: -0.0000

Data Index: 583954 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9066. Min Act: -0.0000

Data Index: 223653 (C4 (Web Text))

Max Activating Token Index: 551