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

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

Neuron 2599 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: 4.2553. Min Range: -4.2553

Max Act: 4.2553. Min Act: -0.0000

Data Index: 574731 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 4.2553. Min Range: -4.2553

Max Act: 3.8244. Min Act: -0.0000

Data Index: 876920 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 4.2553. Min Range: -4.2553

Max Act: 3.7506. Min Act: -0.0000

Data Index: 606998 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 4.2553. Min Range: -4.2553

Max Act: 3.8716. Min Act: -0.0000

Data Index: 991071 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 4.2553. Min Range: -4.2553

Max Act: 3.4050. Min Act: -0.0000

Data Index: 854480 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 4.2553. Min Range: -4.2553

Max Act: 3.0639. Min Act: -0.0000

Data Index: 368251 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 4.2553. Min Range: -4.2553

Max Act: 3.1970. Min Act: -0.0000

Data Index: 548929 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 4.2553. Min Range: -4.2553

Max Act: 3.1923. Min Act: -0.0000

Data Index: 976990 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.9109. Min Act: -0.0000

Data Index: 288927 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 4.2553. Min Range: -4.2553

Max Act: 3.0193. Min Act: -0.0000

Data Index: 138637 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.8098. Min Act: -0.0000

Data Index: 716159 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.8184. Min Act: -0.0000

Data Index: 438612 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.8080. Min Act: -0.0000

Data Index: 519880 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.8698. Min Act: -0.0000

Data Index: 1154338 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.7313. Min Act: -0.0000

Data Index: 451227 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.6036. Min Act: -0.0000

Data Index: 447792 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.8762. Min Act: -0.0000

Data Index: 816703 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.5595. Min Act: -0.0000

Data Index: 42504 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.8511. Min Act: -0.0000

Data Index: 110832 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 4.2553. Min Range: -4.2553

Max Act: 2.6868. Min Act: -0.0000

Data Index: 1078410 (C4 (Web Text))

Max Activating Token Index: 668