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

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

Neuron 3263 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3295. Min Range: -1.3295

Max Act: 1.3295. Min Act: -0.0000

Data Index: 605140 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.3295. Min Range: -1.3295

Max Act: 1.1973. Min Act: -0.0000

Data Index: 290655 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 1.3295. Min Range: -1.3295

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1054720 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.8934. Min Act: -0.0000

Data Index: 820514 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.9472. Min Act: -0.0000

Data Index: 698361 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7780. Min Act: 0.0000

Data Index: 1111264 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.8185. Min Act: -0.0000

Data Index: 311640 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7508. Min Act: -0.0000

Data Index: 521035 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.8029. Min Act: -0.0000

Data Index: 874079 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7903. Min Act: -0.0000

Data Index: 268662 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7907. Min Act: -0.0000

Data Index: 449677 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7299. Min Act: -0.0000

Data Index: 848882 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7697. Min Act: -0.0000

Data Index: 461890 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1316269 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7613. Min Act: -0.0000

Data Index: 848843 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7378. Min Act: -0.0000

Data Index: 60276 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7367. Min Act: -0.0000

Data Index: 244830 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1023018 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1273664 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 1.3295. Min Range: -1.3295

Max Act: 0.7004. Min Act: 0.0001

Data Index: 369589 (C4 (Web Text))

Max Activating Token Index: 846