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

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

Neuron 3907 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.4264. Min Act: -0.0000

Data Index: 791397 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.0965. Min Act: -0.0000

Data Index: 1350368 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.0900. Min Act: -0.0000

Data Index: 741406 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.3717. Min Act: -0.0000

Data Index: 882519 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.0349. Min Act: -0.0000

Data Index: 1339141 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.1099. Min Act: -0.0000

Data Index: 555134 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.8762. Min Act: -0.0000

Data Index: 21020 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.2094. Min Act: -0.0000

Data Index: 842035 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.0218. Min Act: -0.0000

Data Index: 1028698 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.7207. Min Act: -0.0000

Data Index: 426432 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.6465. Min Act: -0.0000

Data Index: 345811 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.8002. Min Act: -0.0000

Data Index: 369559 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.6725. Min Act: -0.0000

Data Index: 799114 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.7543. Min Act: -0.0000

Data Index: 629073 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.7449. Min Act: -0.0000

Data Index: 668730 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.5777. Min Act: -0.0000

Data Index: 1558959 (Python Code)

Max Activating Token Index: 262

Text #16

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.9089. Min Act: -0.0000

Data Index: 475420 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.5276. Min Act: -0.0000

Data Index: 766576 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.7457. Min Act: -0.0000

Data Index: 569834 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 5.4264. Min Range: -5.4264

Max Act: 3.7036. Min Act: -0.0000

Data Index: 1021450 (C4 (Web Text))

Max Activating Token Index: 770