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

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

Neuron 2620 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.9370. Min Act: -0.0000

Data Index: 473278 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5306. Min Act: -0.0000

Data Index: 293935 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5304. Min Act: -0.0001

Data Index: 1032142 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5200. Min Act: -0.0000

Data Index: 471384 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4736. Min Act: -0.0000

Data Index: 987107 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5096. Min Act: -0.0000

Data Index: 308755 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4721. Min Act: -0.0001

Data Index: 239951 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4670. Min Act: 0.0001

Data Index: 357013 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4642. Min Act: -0.0000

Data Index: 437476 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1033012 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4575. Min Act: 0.0001

Data Index: 447409 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4537. Min Act: -0.0000

Data Index: 672826 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1104091 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4262. Min Act: -0.0001

Data Index: 212813 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4113. Min Act: -0.0000

Data Index: 593400 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4173. Min Act: -0.0001

Data Index: 640518 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4302. Min Act: -0.0000

Data Index: 398056 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4272. Min Act: -0.0001

Data Index: 889875 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4215. Min Act: -0.0000

Data Index: 54057 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4131. Min Act: -0.0001

Data Index: 878125 (C4 (Web Text))

Max Activating Token Index: 41