Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 675 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.3010. Min Act: -0.0002

Data Index: 215290 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.3099. Min Act: -0.0002

Data Index: 819840 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2841. Min Act: -0.0002

Data Index: 679576 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2945. Min Act: -0.0002

Data Index: 1140954 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.3020. Min Act: -0.0002

Data Index: 336515 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.3095. Min Act: -0.0001

Data Index: 745289 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2822. Min Act: -0.0001

Data Index: 1238207 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2831. Min Act: -0.0001

Data Index: 465627 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.3122. Min Act: -0.0002

Data Index: 483600 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2721. Min Act: -0.0002

Data Index: 646232 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2978. Min Act: -0.0002

Data Index: 387567 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2902. Min Act: -0.0002

Data Index: 1123682 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2869. Min Act: -0.0001

Data Index: 830868 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2505. Min Act: -0.0002

Data Index: 1061510 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2588. Min Act: -0.0001

Data Index: 486690 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2643. Min Act: -0.0002

Data Index: 931161 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2547. Min Act: -0.0002

Data Index: 1311198 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2527. Min Act: -0.0002

Data Index: 14431 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2416. Min Act: -0.0002

Data Index: 1073352 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2302. Min Act: -0.0002

Data Index: 136334 (C4 (Web Text))

Max Activating Token Index: 970