Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2757 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1009842 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.3044. Min Act: -0.0000

Data Index: 35679 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1305882 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2972. Min Act: -0.0000

Data Index: 276206 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1001976 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1496 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.3027. Min Act: -0.0000

Data Index: 353677 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2780. Min Act: -0.0000

Data Index: 674704 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2651. Min Act: -0.0000

Data Index: 419599 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2613. Min Act: -0.0000

Data Index: 975927 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2681. Min Act: -0.0000

Data Index: 866421 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2597. Min Act: -0.0000

Data Index: 271199 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2481. Min Act: 0.0000

Data Index: 1422269 (Python Code)

Max Activating Token Index: 696

Text #13

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2587. Min Act: -0.0000

Data Index: 292636 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1498069 (Python Code)

Max Activating Token Index: 174

Text #15

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1496487 (Python Code)

Max Activating Token Index: 46

Text #16

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2391. Min Act: -0.0000

Data Index: 445943 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2418. Min Act: -0.0000

Data Index: 312157 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2328. Min Act: -0.0000

Data Index: 974503 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.5122. Min Range: -0.5122

Max Act: 0.2401. Min Act: -0.0000

Data Index: 236444 (C4 (Web Text))

Max Activating Token Index: 32