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

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

Neuron 4360 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: 1.5403. Min Range: -1.5403

Max Act: 1.5403. Min Act: -0.0000

Data Index: 865695 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.5146. Min Act: -0.0000

Data Index: 345996 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.5230. Min Act: -0.0000

Data Index: 768356 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.4075. Min Act: 0.0000

Data Index: 1276338 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.3198. Min Act: -0.0000

Data Index: 1218767 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.4409. Min Act: -0.0000

Data Index: 1063236 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.4273. Min Act: -0.0000

Data Index: 59480 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.3401. Min Act: -0.0000

Data Index: 486203 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2959. Min Act: -0.0000

Data Index: 976892 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2451. Min Act: -0.0000

Data Index: 456124 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.3007. Min Act: -0.0000

Data Index: 36102 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2145. Min Act: -0.0000

Data Index: 86749 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2190. Min Act: -0.0000

Data Index: 445787 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2133. Min Act: -0.0000

Data Index: 312658 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1972. Min Act: -0.0000

Data Index: 353892 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1266050 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1599. Min Act: -0.0000

Data Index: 553395 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1655. Min Act: -0.0000

Data Index: 361456 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2296. Min Act: -0.0000

Data Index: 1213589 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1284. Min Act: -0.0000

Data Index: 495608 (C4 (Web Text))

Max Activating Token Index: 872