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

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

Neuron 5840 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.8078. Min Act: -0.0000

Data Index: 704222 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.6814. Min Act: -0.0000

Data Index: 474386 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1199087 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.5950. Min Act: -0.0000

Data Index: 496684 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.5436. Min Act: -0.0000

Data Index: 516138 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.4547. Min Act: -0.0000

Data Index: 1020383 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.3919. Min Act: -0.0000

Data Index: 808156 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.5007. Min Act: -0.0000

Data Index: 508630 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.3884. Min Act: -0.0000

Data Index: 277460 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.3107. Min Act: -0.0000

Data Index: 164258 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.3782. Min Act: -0.0000

Data Index: 804355 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.3713. Min Act: 0.0000

Data Index: 409371 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.3720. Min Act: -0.0000

Data Index: 1167791 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.2674. Min Act: -0.0000

Data Index: 848984 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.2549. Min Act: -0.0000

Data Index: 946076 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.2427. Min Act: -0.0000

Data Index: 625034 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.3290. Min Act: -0.0000

Data Index: 363496 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1344792 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.3070. Min Act: -0.0000

Data Index: 314113 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 1.8078. Min Range: -1.8078

Max Act: 1.2915. Min Act: -0.0000

Data Index: 786905 (C4 (Web Text))

Max Activating Token Index: 729