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

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

Neuron 4830 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.7408. Min Act: -0.0000

Data Index: 1322918 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.4670. Min Act: -0.0000

Data Index: 911064 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.2883. Min Act: -0.0000

Data Index: 107106 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.0910. Min Act: -0.0000

Data Index: 1321053 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.4128. Min Act: -0.0000

Data Index: 47693 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.1559. Min Act: -0.0000

Data Index: 817999 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.0733. Min Act: -0.0000

Data Index: 597756 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.0715. Min Act: -0.0000

Data Index: 690477 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 2.7408. Min Range: -2.7408

Max Act: 1.9441. Min Act: -0.0000

Data Index: 213673 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.0378. Min Act: -0.0000

Data Index: 395944 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.0343. Min Act: -0.0000

Data Index: 1092429 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.0232. Min Act: -0.0000

Data Index: 366401 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.0040. Min Act: -0.0000

Data Index: 418118 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 2.7408. Min Range: -2.7408

Max Act: 1.9844. Min Act: -0.0000

Data Index: 786115 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 2.7408. Min Range: -2.7408

Max Act: 1.9679. Min Act: -0.0000

Data Index: 1318028 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.0738. Min Act: -0.0000

Data Index: 497496 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 2.7408. Min Range: -2.7408

Max Act: 2.0757. Min Act: -0.0000

Data Index: 363350 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 2.7408. Min Range: -2.7408

Max Act: 1.9421. Min Act: -0.0000

Data Index: 208564 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 2.7408. Min Range: -2.7408

Max Act: 1.8910. Min Act: -0.0000

Data Index: 1140313 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 2.7408. Min Range: -2.7408

Max Act: 1.8791. Min Act: -0.0000

Data Index: 235509 (C4 (Web Text))

Max Activating Token Index: 676