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

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

Neuron 4759 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.7549. Min Act: -0.0000

Data Index: 1025645 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.7164. Min Act: -0.0000

Data Index: 518702 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 4.0587. Min Range: -4.0587

Max Act: 4.0587. Min Act: -0.0000

Data Index: 1206049 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8605. Min Act: -0.0000

Data Index: 315334 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.9762. Min Act: -0.0000

Data Index: 807470 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.6443. Min Act: -0.0000

Data Index: 427008 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.5752. Min Act: -0.0000

Data Index: 636270 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.5231. Min Act: -0.0000

Data Index: 1214066 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.6531. Min Act: -0.0000

Data Index: 278988 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.4837. Min Act: -0.0000

Data Index: 962698 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.3754. Min Act: -0.0000

Data Index: 883993 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.5292. Min Act: -0.0000

Data Index: 1042076 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.2954. Min Act: -0.0000

Data Index: 1323473 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.2750. Min Act: -0.0000

Data Index: 775577 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.2665. Min Act: -0.0000

Data Index: 1185144 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.4002. Min Act: -0.0000

Data Index: 171276 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.1409. Min Act: -0.0000

Data Index: 70873 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 4.0587. Min Range: -4.0587

Max Act: 2.8828. Min Act: -0.0000

Data Index: 422402 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.0075. Min Act: -0.0000

Data Index: 127248 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.1074. Min Act: -0.0000

Data Index: 254179 (C4 (Web Text))

Max Activating Token Index: 270