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

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

Neuron 2233 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.8350. Min Act: -0.0000

Data Index: 463734 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.7130. Min Act: -0.0000

Data Index: 692033 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.7218. Min Act: -0.0000

Data Index: 42591 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.6238. Min Act: -0.0000

Data Index: 539979 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.5503. Min Act: -0.0000

Data Index: 959710 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.4441. Min Act: -0.0000

Data Index: 495845 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.5053. Min Act: -0.0000

Data Index: 1321345 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1125920 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.4231. Min Act: -0.0000

Data Index: 1230488 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.4872. Min Act: -0.0000

Data Index: 136872 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.4714. Min Act: -0.0000

Data Index: 227495 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.3495. Min Act: -0.0000

Data Index: 828493 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.3508. Min Act: -0.0000

Data Index: 170552 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.4083. Min Act: -0.0000

Data Index: 288987 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.3259. Min Act: -0.0000

Data Index: 432048 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2964. Min Act: -0.0000

Data Index: 741521 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2958. Min Act: -0.0000

Data Index: 200633 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2323. Min Act: -0.0000

Data Index: 990498 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1103344 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2686. Min Act: -0.0000

Data Index: 955539 (C4 (Web Text))

Max Activating Token Index: 402