Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2729 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2183. Min Range: -2.2183

Max Act: 2.2183. Min Act: -0.0000

Data Index: 759106 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 2.2183. Min Range: -2.2183

Max Act: 2.0829. Min Act: -0.0000

Data Index: 458040 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.9737. Min Act: -0.0000

Data Index: 1082941 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 2.2183. Min Range: -2.2183

Max Act: 2.0001. Min Act: -0.0000

Data Index: 1357421 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.6546. Min Act: -0.0000

Data Index: 752209 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.6469. Min Act: -0.0000

Data Index: 358444 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.7212. Min Act: -0.0000

Data Index: 923707 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.8059. Min Act: -0.0000

Data Index: 326597 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.6674. Min Act: -0.0000

Data Index: 259961 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.5552. Min Act: -0.0000

Data Index: 448062 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.4242. Min Act: -0.0000

Data Index: 1094174 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.4601. Min Act: -0.0000

Data Index: 871907 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.3710. Min Act: -0.0000

Data Index: 232689 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.4206. Min Act: -0.0000

Data Index: 362045 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.4479. Min Act: -0.0000

Data Index: 20979 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.4823. Min Act: -0.0000

Data Index: 457060 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.4494. Min Act: -0.0000

Data Index: 562199 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.3717. Min Act: -0.0000

Data Index: 664182 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.4843. Min Act: -0.0000

Data Index: 753179 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 2.2183. Min Range: -2.2183

Max Act: 1.4071. Min Act: -0.0000

Data Index: 543232 (C4 (Web Text))

Max Activating Token Index: 287