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

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

Neuron 3990 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6967. Min Act: -0.0000

Data Index: 966988 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1020799 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1113108 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6563. Min Act: -0.0000

Data Index: 968608 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6174. Min Act: -0.0000

Data Index: 529441 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5683. Min Act: -0.0000

Data Index: 810025 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5534. Min Act: -0.0000

Data Index: 341061 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5491. Min Act: -0.0000

Data Index: 269203 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5052. Min Act: -0.0000

Data Index: 978458 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4781. Min Act: -0.0000

Data Index: 282811 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4961. Min Act: -0.0000

Data Index: 166634 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1268904 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4334. Min Act: -0.0000

Data Index: 151953 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1158226 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4230. Min Act: -0.0000

Data Index: 421370 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4345. Min Act: -0.0000

Data Index: 799218 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1157301 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4205. Min Act: -0.0000

Data Index: 298247 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4098. Min Act: -0.0000

Data Index: 348607 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4052. Min Act: -0.0000

Data Index: 418589 (C4 (Web Text))

Max Activating Token Index: 55