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

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

Neuron 657 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4180. Min Range: -4.4180

Max Act: 4.4180. Min Act: -0.0000

Data Index: 1165767 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 4.4180. Min Range: -4.4180

Max Act: 4.1360. Min Act: -0.0000

Data Index: 1217774 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.7793. Min Act: -0.0000

Data Index: 607952 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.6294. Min Act: -0.0000

Data Index: 908765 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.7099. Min Act: -0.0000

Data Index: 1040096 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.5529. Min Act: -0.0000

Data Index: 1156104 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.8876. Min Act: -0.0000

Data Index: 314116 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.8737. Min Act: -0.0000

Data Index: 536293 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.3791. Min Act: -0.0000

Data Index: 1327482 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.5244. Min Act: -0.0000

Data Index: 166868 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.5432. Min Act: -0.0000

Data Index: 260668 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.7170. Min Act: -0.0000

Data Index: 662728 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.2478. Min Act: -0.0000

Data Index: 384126 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.5182. Min Act: -0.0000

Data Index: 799542 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.5043. Min Act: -0.0000

Data Index: 544118 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.3009. Min Act: -0.0000

Data Index: 626473 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.5643. Min Act: -0.0000

Data Index: 398379 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.3767. Min Act: -0.0000

Data Index: 879425 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.2408. Min Act: -0.0000

Data Index: 168129 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 4.4180. Min Range: -4.4180

Max Act: 3.3660. Min Act: -0.0000

Data Index: 1279158 (C4 (Web Text))

Max Activating Token Index: 608