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

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

Neuron 1341 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.5227. Min Act: -0.0000

Data Index: 482643 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.5569. Min Act: -0.0001

Data Index: 1136166 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.4229. Min Act: -0.0001

Data Index: 754897 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.4456. Min Act: -0.0000

Data Index: 1175123 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1070513 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.3428. Min Act: -0.0000

Data Index: 780983 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.3991. Min Act: -0.0000

Data Index: 155868 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.4582. Min Act: -0.0000

Data Index: 807653 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.5176. Min Act: -0.0000

Data Index: 1606361 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1021642 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.3345. Min Act: -0.0000

Data Index: 1337637 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.2883. Min Act: -0.0000

Data Index: 1131648 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.4185. Min Act: -0.0000

Data Index: 655445 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.2764. Min Act: -0.0000

Data Index: 199299 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.3473. Min Act: -0.0000

Data Index: 848383 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.2355. Min Act: -0.0000

Data Index: 847992 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.2301. Min Act: -0.0000

Data Index: 809377 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.2153. Min Act: -0.0000

Data Index: 152088 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.2327. Min Act: -0.0000

Data Index: 905718 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.3501. Min Act: -0.0000

Data Index: 229398 (C4 (Web Text))

Max Activating Token Index: 213