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

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

Neuron 3998 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.4128. Min Act: -0.0001

Data Index: 829372 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3767. Min Act: -0.0001

Data Index: 952054 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3532. Min Act: -0.0001

Data Index: 686969 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3538. Min Act: -0.0000

Data Index: 380179 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3600. Min Act: -0.0001

Data Index: 844187 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3597. Min Act: -0.0001

Data Index: 1236114 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3710. Min Act: -0.0001

Data Index: 551626 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1188042 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3098. Min Act: -0.0000

Data Index: 71704 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3539. Min Act: -0.0000

Data Index: 271272 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3358. Min Act: -0.0001

Data Index: 1152083 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3327. Min Act: -0.0001

Data Index: 812485 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3290. Min Act: -0.0001

Data Index: 804354 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2950. Min Act: -0.0001

Data Index: 461388 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3190. Min Act: -0.0001

Data Index: 214530 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2916. Min Act: -0.0001

Data Index: 176273 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1117343 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3036. Min Act: -0.0001

Data Index: 114006 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2570. Min Act: -0.0001

Data Index: 800350 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2522. Min Act: -0.0001

Data Index: 1215735 (C4 (Web Text))

Max Activating Token Index: 511