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

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

Neuron 4399 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.5292. Min Act: -0.0001

Data Index: 920957 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.3362. Min Act: -0.0001

Data Index: 486351 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.2986. Min Act: -0.0001

Data Index: 662417 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.2742. Min Act: -0.0001

Data Index: 557399 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.2068. Min Act: -0.0001

Data Index: 867657 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.2343. Min Act: -0.0001

Data Index: 116965 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0787. Min Act: -0.0001

Data Index: 87660 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.2509. Min Act: -0.0001

Data Index: 258967 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1260. Min Act: -0.0001

Data Index: 561017 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0784. Min Act: -0.0001

Data Index: 326571 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1954. Min Act: -0.0001

Data Index: 569638 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0762. Min Act: -0.0001

Data Index: 1173420 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1295. Min Act: -0.0001

Data Index: 760401 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1524. Min Act: -0.0001

Data Index: 1142416 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1357651 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.2797. Min Act: -0.0001

Data Index: 1122627 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0894. Min Act: -0.0001

Data Index: 1195577 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1176. Min Act: -0.0001

Data Index: 185004 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0039. Min Act: -0.0001

Data Index: 1277119 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0875. Min Act: -0.0000

Data Index: 509724 (C4 (Web Text))

Max Activating Token Index: 122