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

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

Neuron 2577 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.6803. Min Act: -0.0000

Data Index: 1313430 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.6972. Min Act: -0.0000

Data Index: 206965 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.6969. Min Act: -0.0000

Data Index: 394176 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.6272. Min Act: -0.0000

Data Index: 319002 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.5461. Min Act: -0.0000

Data Index: 468803 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.3964. Min Act: -0.0000

Data Index: 1304070 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.4972. Min Act: -0.0000

Data Index: 1345407 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.2511. Min Act: -0.0000

Data Index: 89173 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.3294. Min Act: -0.0000

Data Index: 76267 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1353715 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.3893. Min Act: -0.0000

Data Index: 849973 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.3125. Min Act: -0.0000

Data Index: 944852 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.2110. Min Act: -0.0000

Data Index: 535512 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.3334. Min Act: -0.0000

Data Index: 1045040 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.2303. Min Act: -0.0000

Data Index: 836245 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.2978. Min Act: -0.0000

Data Index: 30303 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.2314. Min Act: -0.0000

Data Index: 710015 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.2287. Min Act: -0.0000

Data Index: 622770 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.1873. Min Act: -0.0000

Data Index: 416317 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 1.6972. Min Range: -1.6972

Max Act: 1.2552. Min Act: -0.0000

Data Index: 547111 (C4 (Web Text))

Max Activating Token Index: 1014