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

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

Neuron 2019 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: 3.2923. Min Range: -3.2923

Max Act: 3.2923. Min Act: -0.0000

Data Index: 395046 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.9691. Min Act: -0.0000

Data Index: 1336693 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.9240. Min Act: -0.0000

Data Index: 126207 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.7297. Min Act: -0.0000

Data Index: 405032 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.2639. Min Act: -0.0000

Data Index: 998546 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.5331. Min Act: -0.0000

Data Index: 340070 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.1834. Min Act: 0.0000

Data Index: 551366 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.1950. Min Act: -0.0000

Data Index: 22315 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.2217. Min Act: -0.0000

Data Index: 154871 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.0267. Min Act: -0.0000

Data Index: 970455 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 3.2923. Min Range: -3.2923

Max Act: 1.8751. Min Act: -0.0000

Data Index: 783862 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 3.2923. Min Range: -3.2923

Max Act: 1.8583. Min Act: -0.0000

Data Index: 474789 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 3.2923. Min Range: -3.2923

Max Act: 1.8156. Min Act: -0.0000

Data Index: 1330688 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 3.2923. Min Range: -3.2923

Max Act: 1.7737. Min Act: -0.0000

Data Index: 1327346 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 3.2923. Min Range: -3.2923

Max Act: 1.7197. Min Act: -0.0000

Data Index: 506545 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 3.2923. Min Range: -3.2923

Max Act: 1.5860. Min Act: -0.0000

Data Index: 465861 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 3.2923. Min Range: -3.2923

Max Act: 1.4671. Min Act: -0.0000

Data Index: 911126 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 3.2923. Min Range: -3.2923

Max Act: 1.6397. Min Act: -0.0000

Data Index: 775877 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 3.2923. Min Range: -3.2923

Max Act: 1.6326. Min Act: -0.0000

Data Index: 714988 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 3.2923. Min Range: -3.2923

Max Act: 1.5360. Min Act: -0.0000

Data Index: 834592 (C4 (Web Text))

Max Activating Token Index: 624