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

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

Neuron 2770 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.4459. Min Act: -0.0001

Data Index: 6749 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3903. Min Act: -0.0001

Data Index: 818019 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.2700. Min Act: -0.0000

Data Index: 855364 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.2516. Min Act: -0.0000

Data Index: 163427 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.2100. Min Act: -0.0001

Data Index: 635285 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.2331. Min Act: -0.0000

Data Index: 245810 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.2063. Min Act: -0.0000

Data Index: 953143 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1059925 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.1862. Min Act: -0.0001

Data Index: 82247 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.1972. Min Act: -0.0000

Data Index: 484676 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.2040. Min Act: -0.0001

Data Index: 975607 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.2059. Min Act: -0.0001

Data Index: 690194 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.2042. Min Act: -0.0001

Data Index: 67850 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.1969. Min Act: -0.0000

Data Index: 163659 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.1924. Min Act: -0.0000

Data Index: 895751 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.1884. Min Act: -0.0001

Data Index: 440783 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.1823. Min Act: -0.0001

Data Index: 224631 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1273835 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.1900. Min Act: -0.0001

Data Index: 438606 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.1771. Min Act: -0.0001

Data Index: 749474 (C4 (Web Text))

Max Activating Token Index: 377