Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1589 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9875. Min Act: -0.0000

Data Index: 962117 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9873. Min Act: -0.0000

Data Index: 881168 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9579. Min Act: -0.0000

Data Index: 819099 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1008251 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9772. Min Act: -0.0000

Data Index: 521852 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8916. Min Act: -0.0000

Data Index: 1438014 (Python Code)

Max Activating Token Index: 281

Text #6

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1176370 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1315368 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1071823 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8469. Min Act: -0.0000

Data Index: 953549 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8224. Min Act: -0.0000

Data Index: 8517 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8360. Min Act: -0.0000

Data Index: 684521 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1576491 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1105874 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.6846. Min Act: -0.0000

Data Index: 171197 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7945. Min Act: -0.0000

Data Index: 367402 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1264009 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7849. Min Act: -0.0000

Data Index: 131996 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7529. Min Act: -0.0000

Data Index: 585263 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1132666 (C4 (Web Text))

Max Activating Token Index: 355