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

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

Neuron 920 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0598. Min Range: -2.0598

Max Act: 2.0598. Min Act: -0.0000

Data Index: 1297580 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.8278. Min Act: -0.0000

Data Index: 1300805 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.8665. Min Act: -0.0000

Data Index: 1102569 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.7597. Min Act: -0.0000

Data Index: 698450 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.5314. Min Act: -0.0000

Data Index: 1294731 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.5861. Min Act: -0.0000

Data Index: 1289188 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.4740. Min Act: -0.0000

Data Index: 307751 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.5629. Min Act: -0.0000

Data Index: 921339 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.5383. Min Act: -0.0000

Data Index: 1089888 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.4960. Min Act: -0.0000

Data Index: 996406 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.4758. Min Act: -0.0000

Data Index: 595015 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.4732. Min Act: -0.0000

Data Index: 333704 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.5518. Min Act: -0.0000

Data Index: 544253 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.5307. Min Act: -0.0000

Data Index: 914858 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.4842. Min Act: -0.0000

Data Index: 660628 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.4215. Min Act: -0.0000

Data Index: 968921 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.4186. Min Act: 0.0001

Data Index: 192410 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.4170. Min Act: 0.0000

Data Index: 913636 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.3254. Min Act: -0.0000

Data Index: 1298192 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 2.0598. Min Range: -2.0598

Max Act: 1.3952. Min Act: 0.0000

Data Index: 37099 (C4 (Web Text))

Max Activating Token Index: 549