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

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

Neuron 4707 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.7328. Min Act: -0.0000

Data Index: 706926 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.5492. Min Act: -0.0000

Data Index: 1487878 (Python Code)

Max Activating Token Index: 172

Text #2

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.6713. Min Act: -0.0000

Data Index: 329946 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.5146. Min Act: -0.0000

Data Index: 1587754 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.6198. Min Act: -0.0000

Data Index: 506359 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.5782. Min Act: -0.0000

Data Index: 1090613 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.5823. Min Act: -0.0000

Data Index: 821430 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.3974. Min Act: -0.0000

Data Index: 1416967 (Python Code)

Max Activating Token Index: 946

Text #8

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.4921. Min Act: -0.0000

Data Index: 1275288 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.4896. Min Act: -0.0000

Data Index: 249195 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.3605. Min Act: -0.0000

Data Index: 585001 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.2640. Min Act: -0.0000

Data Index: 184276 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.3801. Min Act: -0.0000

Data Index: 885256 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.3454. Min Act: -0.0000

Data Index: 805021 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.6019. Min Act: -0.0000

Data Index: 1363687 (Python Code)

Max Activating Token Index: 125

Text #15

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.2212. Min Act: -0.0000

Data Index: 454726 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.4382. Min Act: -0.0000

Data Index: 266871 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 2.7328. Min Range: -2.7328

Max Act: 1.9822. Min Act: -0.0000

Data Index: 1633467 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.4487. Min Act: -0.0000

Data Index: 1024928 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 2.7328. Min Range: -2.7328

Max Act: 2.1325. Min Act: -0.0000

Data Index: 500722 (C4 (Web Text))

Max Activating Token Index: 649