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

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

Neuron 5588 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.8290. Min Act: -0.0000

Data Index: 1317424 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7508. Min Act: -0.0000

Data Index: 473629 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.5946. Min Act: -0.0000

Data Index: 976243 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.4461. Min Act: -0.0000

Data Index: 815228 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1002348 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.5622. Min Act: -0.0000

Data Index: 1078815 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.4177. Min Act: -0.0000

Data Index: 209417 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.3928. Min Act: -0.0000

Data Index: 281377 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.4363. Min Act: -0.0000

Data Index: 674407 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.3066. Min Act: -0.0000

Data Index: 1039513 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.3146. Min Act: -0.0000

Data Index: 61137 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1092623 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.2090. Min Act: -0.0000

Data Index: 1167802 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.2751. Min Act: -0.0000

Data Index: 520136 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.2616. Min Act: -0.0000

Data Index: 884864 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1159767 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.2732. Min Act: -0.0000

Data Index: 366405 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.2310. Min Act: -0.0000

Data Index: 790187 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.1903. Min Act: -0.0000

Data Index: 396506 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.1923. Min Act: -0.0000

Data Index: 348559 (C4 (Web Text))

Max Activating Token Index: 952