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

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

Neuron 4733 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: 0.5987. Min Range: -0.5987

Max Act: 0.5987. Min Act: -0.0000

Data Index: 857356 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.5190. Min Act: -0.0000

Data Index: 592557 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1032709 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4889. Min Act: -0.0000

Data Index: 18953 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4504. Min Act: -0.0000

Data Index: 887579 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4168. Min Act: -0.0000

Data Index: 795195 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4450. Min Act: -0.0000

Data Index: 624632 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4204. Min Act: -0.0000

Data Index: 698320 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4418. Min Act: -0.0000

Data Index: 890293 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4213. Min Act: -0.0000

Data Index: 388945 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.3996. Min Act: -0.0000

Data Index: 457932 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1233711 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4392. Min Act: -0.0000

Data Index: 885852 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4319. Min Act: -0.0000

Data Index: 354007 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1155029 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4137. Min Act: -0.0000

Data Index: 938103 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4227. Min Act: 0.0000

Data Index: 1165195 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4028. Min Act: -0.0000

Data Index: 536511 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4069. Min Act: -0.0000

Data Index: 209683 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.5987. Min Range: -0.5987

Max Act: 0.4209. Min Act: -0.0000

Data Index: 258466 (C4 (Web Text))

Max Activating Token Index: 671