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

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

Neuron 5280 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: 1.0440. Min Range: -1.0440

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1037835 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9433. Min Act: -0.0000

Data Index: 823435 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8945. Min Act: -0.0000

Data Index: 631283 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1272744 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7984. Min Act: -0.0000

Data Index: 625904 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7474. Min Act: -0.0000

Data Index: 286137 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6433. Min Act: -0.0000

Data Index: 11435 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6632. Min Act: -0.0000

Data Index: 893658 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6979. Min Act: -0.0000

Data Index: 605433 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6903. Min Act: -0.0000

Data Index: 360008 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6566. Min Act: -0.0000

Data Index: 833339 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6975. Min Act: -0.0000

Data Index: 898275 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1337431 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6823. Min Act: -0.0000

Data Index: 535984 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6400. Min Act: -0.0000

Data Index: 410700 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6716. Min Act: -0.0000

Data Index: 74815 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7077. Min Act: -0.0000

Data Index: 521262 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6480. Min Act: -0.0000

Data Index: 785964 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6542. Min Act: -0.0000

Data Index: 13250 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6168. Min Act: -0.0000

Data Index: 673193 (C4 (Web Text))

Max Activating Token Index: 54