Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3932 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.7946. Min Act: -0.0000

Data Index: 107790 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.7471. Min Act: -0.0000

Data Index: 140598 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6710. Min Act: -0.0000

Data Index: 797281 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6654. Min Act: 0.0000

Data Index: 509998 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6837. Min Act: 0.0000

Data Index: 310385 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6413. Min Act: 0.0000

Data Index: 266160 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6161. Min Act: -0.0000

Data Index: 998273 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6375. Min Act: -0.0000

Data Index: 615717 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1287052 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1356170 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6306. Min Act: -0.0000

Data Index: 207286 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6080. Min Act: -0.0000

Data Index: 241258 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5622. Min Act: 0.0000

Data Index: 1264075 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5597. Min Act: -0.0000

Data Index: 280478 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1102481 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5537. Min Act: -0.0000

Data Index: 732380 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5619. Min Act: -0.0000

Data Index: 198887 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1143134 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5570. Min Act: -0.0000

Data Index: 539650 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5510. Min Act: -0.0000

Data Index: 785684 (C4 (Web Text))

Max Activating Token Index: 99