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

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

Neuron 3293 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: 1.9084. Min Range: -1.9084

Max Act: 1.8070. Min Act: -0.0000

Data Index: 193125 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.7313. Min Act: -0.0000

Data Index: 363182 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.9084. Min Act: -0.0000

Data Index: 1183852 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.7337. Min Act: -0.0000

Data Index: 1117840 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.6354. Min Act: -0.0000

Data Index: 173242 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.5832. Min Act: -0.0000

Data Index: 1188269 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.5503. Min Act: -0.0000

Data Index: 343025 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.6205. Min Act: -0.0000

Data Index: 282555 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.5508. Min Act: -0.0000

Data Index: 365755 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.4833. Min Act: -0.0000

Data Index: 394194 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.4386. Min Act: -0.0000

Data Index: 9025 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.3444. Min Act: -0.0000

Data Index: 287920 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.4324. Min Act: -0.0000

Data Index: 748034 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.3496. Min Act: -0.0000

Data Index: 491732 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.4242. Min Act: -0.0000

Data Index: 339541 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.3292. Min Act: -0.0000

Data Index: 864396 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.3745. Min Act: -0.0000

Data Index: 1231917 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.3667. Min Act: -0.0000

Data Index: 746187 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.3165. Min Act: -0.0000

Data Index: 431504 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 1.9084. Min Range: -1.9084

Max Act: 1.3125. Min Act: -0.0000

Data Index: 614756 (C4 (Web Text))

Max Activating Token Index: 703