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

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

Neuron 3860 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: 2.2598. Min Range: -2.2598

Max Act: 2.1964. Min Act: -0.0000

Data Index: 636603 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.2598. Min Range: -2.2598

Max Act: 2.2598. Min Act: -0.0000

Data Index: 1154655 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.9466. Min Act: -0.0000

Data Index: 1192329 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.8008. Min Act: -0.0000

Data Index: 1279401 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 2.2598. Min Range: -2.2598

Max Act: 2.0834. Min Act: -0.0000

Data Index: 479044 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.6641. Min Act: -0.0000

Data Index: 18062 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.8203. Min Act: -0.0000

Data Index: 1165199 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.5515. Min Act: -0.0000

Data Index: 1348950 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.6478. Min Act: -0.0000

Data Index: 1144480 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.6492. Min Act: -0.0000

Data Index: 85175 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.6460. Min Act: -0.0000

Data Index: 712987 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.6916. Min Act: -0.0000

Data Index: 622387 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.7760. Min Act: -0.0000

Data Index: 639755 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.5856. Min Act: -0.0000

Data Index: 1171055 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.4701. Min Act: -0.0000

Data Index: 66976 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.6824. Min Act: -0.0000

Data Index: 288152 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.6129. Min Act: -0.0000

Data Index: 60994 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.2456. Min Act: -0.0000

Data Index: 1309263 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.4203. Min Act: -0.0000

Data Index: 194950 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 2.2598. Min Range: -2.2598

Max Act: 1.3671. Min Act: -0.0000

Data Index: 1223728 (C4 (Web Text))

Max Activating Token Index: 387