Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 987 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.5228. Min Range: -2.5228

Max Act: 2.5228. Min Act: -0.0000

Data Index: 1248721 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.9196. Min Act: -0.0000

Data Index: 615168 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.8932. Min Act: -0.0001

Data Index: 881994 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.9250. Min Act: -0.0001

Data Index: 94360 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.8313. Min Act: -0.0001

Data Index: 1045829 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.8106. Min Act: -0.0001

Data Index: 931296 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1101211 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.7623. Min Act: -0.0001

Data Index: 753889 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.8114. Min Act: -0.0000

Data Index: 312306 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.7802. Min Act: -0.0000

Data Index: 487406 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1084698 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.7451. Min Act: -0.0001

Data Index: 652183 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.7342. Min Act: -0.0001

Data Index: 84493 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.7179. Min Act: -0.0001

Data Index: 900996 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.7528. Min Act: -0.0000

Data Index: 958333 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.7318. Min Act: -0.0001

Data Index: 1037410 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.7028. Min Act: -0.0000

Data Index: 170199 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.6948. Min Act: -0.0001

Data Index: 1342482 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.7006. Min Act: -0.0001

Data Index: 146872 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 2.5228. Min Range: -2.5228

Max Act: 0.6628. Min Act: -0.0000

Data Index: 518453 (C4 (Web Text))

Max Activating Token Index: 95