Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1989 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.2728. Min Range: -8.2728

Max Act: 8.2728. Min Act: -0.0000

Data Index: 971898 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 8.2728. Min Range: -8.2728

Max Act: 8.1226. Min Act: -0.0000

Data Index: 989992 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 8.2728. Min Range: -8.2728

Max Act: 6.9584. Min Act: -0.0000

Data Index: 1079036 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 8.2728. Min Range: -8.2728

Max Act: 6.0554. Min Act: -0.0000

Data Index: 449127 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 8.2728. Min Range: -8.2728

Max Act: 5.8925. Min Act: -0.0000

Data Index: 1095759 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.6329. Min Act: -0.0000

Data Index: 377553 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.5315. Min Act: -0.0000

Data Index: 1194411 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.7714. Min Act: -0.0000

Data Index: 328824 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.7313. Min Act: -0.0000

Data Index: 478569 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.0268. Min Act: -0.0000

Data Index: 307888 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 8.2728. Min Range: -8.2728

Max Act: 5.7738. Min Act: -0.0000

Data Index: 867737 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.2085. Min Act: -0.0000

Data Index: 891679 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 8.2728. Min Range: -8.2728

Max Act: 3.8968. Min Act: -0.0000

Data Index: 460800 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.6467. Min Act: -0.0000

Data Index: 994272 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.5417. Min Act: -0.0000

Data Index: 644173 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.9195. Min Act: -0.0000

Data Index: 528982 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.2286. Min Act: -0.0000

Data Index: 861545 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.4144. Min Act: -0.0000

Data Index: 423308 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 8.2728. Min Range: -8.2728

Max Act: 4.2573. Min Act: -0.0000

Data Index: 566929 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 8.2728. Min Range: -8.2728

Max Act: 3.9643. Min Act: -0.0000

Data Index: 250746 (C4 (Web Text))

Max Activating Token Index: 576