Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1006 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.2499. Min Range: -4.2499

Max Act: 4.2499. Min Act: -0.0001

Data Index: 812541 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 4.2499. Min Range: -4.2499

Max Act: 4.0431. Min Act: -0.0001

Data Index: 1310894 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.9901. Min Act: -0.0001

Data Index: 979120 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.9604. Min Act: -0.0001

Data Index: 490974 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.8503. Min Act: -0.0001

Data Index: 186254 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.7327. Min Act: -0.0001

Data Index: 889421 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.7952. Min Act: -0.0001

Data Index: 1004571 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.6312. Min Act: -0.0001

Data Index: 406957 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.4048. Min Act: -0.0001

Data Index: 116091 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.6833. Min Act: -0.0001

Data Index: 659557 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.5089. Min Act: -0.0001

Data Index: 1073341 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.5086. Min Act: -0.0001

Data Index: 1149780 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.6687. Min Act: -0.0001

Data Index: 998001 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.4939. Min Act: -0.0001

Data Index: 1317908 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.2781. Min Act: -0.0001

Data Index: 915614 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.4389. Min Act: -0.0001

Data Index: 1040855 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.4218. Min Act: -0.0001

Data Index: 762455 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.4177. Min Act: -0.0001

Data Index: 1167600 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.2649. Min Act: -0.0001

Data Index: 1302659 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 4.2499. Min Range: -4.2499

Max Act: 3.2521. Min Act: -0.0001

Data Index: 371328 (C4 (Web Text))

Max Activating Token Index: 475