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

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

Neuron 3749 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: 1.6306. Min Range: -1.6306

Max Act: 1.6306. Min Act: -0.0000

Data Index: 984113 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.3054. Min Act: -0.0000

Data Index: 277026 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.4423. Min Act: -0.0000

Data Index: 1250384 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.3998. Min Act: -0.0000

Data Index: 553732 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.3900. Min Act: -0.0000

Data Index: 143366 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.3640. Min Act: -0.0000

Data Index: 674077 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.2742. Min Act: -0.0000

Data Index: 359703 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.3367. Min Act: -0.0000

Data Index: 420079 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.2506. Min Act: -0.0000

Data Index: 48740 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.2636. Min Act: -0.0000

Data Index: 211783 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.3078. Min Act: -0.0000

Data Index: 445918 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.2819. Min Act: -0.0000

Data Index: 344331 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.2812. Min Act: -0.0000

Data Index: 458274 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1268405 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.3135. Min Act: -0.0000

Data Index: 365810 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.1693. Min Act: -0.0000

Data Index: 720511 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1231484 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.2387. Min Act: -0.0000

Data Index: 1001538 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.2358. Min Act: -0.0000

Data Index: 999589 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.6306. Min Range: -1.6306

Max Act: 1.2099. Min Act: -0.0000

Data Index: 367313 (C4 (Web Text))

Max Activating Token Index: 979