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

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

Neuron 5152 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: 2.6643. Min Range: -2.6643

Max Act: 2.6643. Min Act: -0.0000

Data Index: 1175382 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 2.6643. Min Range: -2.6643

Max Act: 2.2188. Min Act: -0.0000

Data Index: 1132329 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 2.6643. Min Range: -2.6643

Max Act: 2.1672. Min Act: -0.0000

Data Index: 1048192 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 2.6643. Min Range: -2.6643

Max Act: 2.0751. Min Act: -0.0000

Data Index: 984178 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 2.6643. Min Range: -2.6643

Max Act: 2.0318. Min Act: -0.0000

Data Index: 1271354 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 2.6643. Min Range: -2.6643

Max Act: 2.1105. Min Act: -0.0000

Data Index: 118262 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.9886. Min Act: -0.0000

Data Index: 263807 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.9984. Min Act: -0.0000

Data Index: 967382 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.9145. Min Act: -0.0000

Data Index: 225680 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.7053. Min Act: -0.0000

Data Index: 1052510 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.6547. Min Act: -0.0000

Data Index: 460443 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.8685. Min Act: -0.0000

Data Index: 980578 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.6483. Min Act: -0.0000

Data Index: 1198446 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.6518. Min Act: -0.0000

Data Index: 695378 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.7213. Min Act: -0.0000

Data Index: 1201811 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.6832. Min Act: -0.0000

Data Index: 383695 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.6765. Min Act: -0.0000

Data Index: 810640 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.6450. Min Act: -0.0000

Data Index: 497642 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.7378. Min Act: -0.0000

Data Index: 1112883 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 2.6643. Min Range: -2.6643

Max Act: 1.7125. Min Act: -0.0000

Data Index: 922476 (C4 (Web Text))

Max Activating Token Index: 401