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

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

Neuron 620 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5443. Min Act: -0.0000

Data Index: 257925 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5164. Min Act: -0.0000

Data Index: 873000 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4781. Min Act: -0.0000

Data Index: 203126 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4769. Min Act: -0.0000

Data Index: 735824 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4696. Min Act: -0.0000

Data Index: 238520 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4473. Min Act: -0.0000

Data Index: 768732 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1128008 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4235. Min Act: -0.0000

Data Index: 553421 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4466. Min Act: -0.0000

Data Index: 694316 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1227274 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4415. Min Act: -0.0000

Data Index: 248208 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4163. Min Act: -0.0000

Data Index: 509995 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4301. Min Act: -0.0000

Data Index: 119610 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1083248 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4046. Min Act: -0.0000

Data Index: 849946 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1180899 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4155. Min Act: -0.0000

Data Index: 42440 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1286411 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1121182 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4331. Min Act: -0.0000

Data Index: 513811 (C4 (Web Text))

Max Activating Token Index: 447