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

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

Neuron 4100 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7532. Min Act: -0.0000

Data Index: 460967 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1056076 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7004. Min Act: -0.0000

Data Index: 637606 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6688. Min Act: -0.0000

Data Index: 452949 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6910. Min Act: -0.0000

Data Index: 451685 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6747. Min Act: -0.0000

Data Index: 5681 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1278447 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1250921 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6276. Min Act: -0.0000

Data Index: 618838 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1485561 (Python Code)

Max Activating Token Index: 597

Text #10

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6370. Min Act: -0.0000

Data Index: 427932 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1044097 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6377. Min Act: -0.0000

Data Index: 703952 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5941. Min Act: -0.0000

Data Index: 121063 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6096. Min Act: -0.0000

Data Index: 575073 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5831. Min Act: -0.0000

Data Index: 868511 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1520089 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5710. Min Act: -0.0000

Data Index: 810062 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1317478 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1539462 (Python Code)

Max Activating Token Index: 97