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

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

Neuron 5909 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.7374. Min Act: -0.0001

Data Index: 999207 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.8001. Min Act: -0.0001

Data Index: 233181 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4986. Min Act: -0.0001

Data Index: 1090692 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.5919. Min Act: -0.0001

Data Index: 958117 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.7628. Min Act: -0.0001

Data Index: 600950 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4714. Min Act: -0.0001

Data Index: 203496 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.5236. Min Act: -0.0001

Data Index: 706382 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3769. Min Act: -0.0001

Data Index: 248679 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4008. Min Act: -0.0001

Data Index: 16128 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4174. Min Act: -0.0001

Data Index: 598336 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3348. Min Act: -0.0001

Data Index: 422692 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.5756. Min Act: -0.0001

Data Index: 202718 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4804. Min Act: -0.0001

Data Index: 848428 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4205. Min Act: -0.0001

Data Index: 880960 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3911. Min Act: -0.0001

Data Index: 959356 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3278. Min Act: -0.0001

Data Index: 1089984 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3130. Min Act: -0.0001

Data Index: 390170 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4534. Min Act: -0.0001

Data Index: 665475 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.5326. Min Act: -0.0001

Data Index: 468357 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3611. Min Act: -0.0001

Data Index: 906653 (C4 (Web Text))

Max Activating Token Index: 508