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

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

Neuron 4584 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: 1.0096. Min Range: -1.0096

Max Act: 1.0096. Min Act: -0.0000

Data Index: 541527 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1320639 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1337407 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9506. Min Act: -0.0000

Data Index: 12982 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9061. Min Act: -0.0000

Data Index: 403161 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9350. Min Act: -0.0000

Data Index: 912500 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8680. Min Act: -0.0000

Data Index: 927558 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9180. Min Act: -0.0000

Data Index: 409167 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8917. Min Act: -0.0000

Data Index: 560952 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8311. Min Act: -0.0000

Data Index: 866585 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1091660 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1288913 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9070. Min Act: -0.0000

Data Index: 402304 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9227. Min Act: -0.0000

Data Index: 604715 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1143224 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8579. Min Act: -0.0000

Data Index: 716225 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9055. Min Act: -0.0000

Data Index: 42765 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1364451 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9117. Min Act: -0.0000

Data Index: 268121 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9147. Min Act: -0.0000

Data Index: 479750 (C4 (Web Text))

Max Activating Token Index: 482