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

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

Neuron 855 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.8164. Min Act: -0.0000

Data Index: 415423 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.4577. Min Act: -0.0000

Data Index: 606344 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.4630. Min Act: -0.0000

Data Index: 168813 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.5216. Min Act: -0.0000

Data Index: 769831 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.3107. Min Act: -0.0000

Data Index: 1089761 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.3072. Min Act: -0.0000

Data Index: 942634 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.1195. Min Act: -0.0000

Data Index: 1218746 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.3454. Min Act: -0.0000

Data Index: 247350 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.0779. Min Act: -0.0000

Data Index: 581380 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.1692. Min Act: -0.0000

Data Index: 1218518 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.1607. Min Act: -0.0000

Data Index: 1152135 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.1542. Min Act: -0.0000

Data Index: 243974 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.1544. Min Act: -0.0000

Data Index: 433424 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 2.8164. Min Range: -2.8164

Max Act: 1.9482. Min Act: -0.0000

Data Index: 94773 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 2.8164. Min Range: -2.8164

Max Act: 1.9564. Min Act: -0.0000

Data Index: 933144 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 2.8164. Min Range: -2.8164

Max Act: 2.0479. Min Act: -0.0000

Data Index: 3312 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 2.8164. Min Range: -2.8164

Max Act: 1.9836. Min Act: -0.0000

Data Index: 334990 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 2.8164. Min Range: -2.8164

Max Act: 1.7821. Min Act: -0.0000

Data Index: 350226 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 2.8164. Min Range: -2.8164

Max Act: 1.8697. Min Act: -0.0000

Data Index: 970197 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 2.8164. Min Range: -2.8164

Max Act: 1.8820. Min Act: -0.0000

Data Index: 676902 (C4 (Web Text))

Max Activating Token Index: 301