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

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

Neuron 3743 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0424. Min Range: -1.0424

Max Act: 1.0424. Min Act: -0.0000

Data Index: 1222379 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 1.0424. Min Range: -1.0424

Max Act: 1.0324. Min Act: -0.0000

Data Index: 619982 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.9191. Min Act: -0.0000

Data Index: 309737 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.8967. Min Act: -0.0000

Data Index: 468368 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.8482. Min Act: -0.0000

Data Index: 893957 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1165240 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1336790 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6985. Min Act: -0.0000

Data Index: 345337 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1058972 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.7055. Min Act: -0.0000

Data Index: 688054 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.7332. Min Act: -0.0000

Data Index: 449838 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.7296. Min Act: -0.0000

Data Index: 880574 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6690. Min Act: -0.0000

Data Index: 61994 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1191959 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1004858 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6579. Min Act: -0.0000

Data Index: 979139 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6440. Min Act: -0.0000

Data Index: 996209 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6606. Min Act: -0.0000

Data Index: 862665 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6471. Min Act: -0.0000

Data Index: 773176 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1236322 (C4 (Web Text))

Max Activating Token Index: 44