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

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

Neuron 3522 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.7820. Min Act: -0.0001

Data Index: 1065245 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.7365. Min Act: -0.0001

Data Index: 1051076 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.7022. Min Act: -0.0001

Data Index: 975631 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.5931. Min Act: -0.0001

Data Index: 311831 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.5438. Min Act: -0.0001

Data Index: 921656 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.5659. Min Act: -0.0001

Data Index: 722891 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.6297. Min Act: -0.0001

Data Index: 1011696 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.5786. Min Act: -0.0001

Data Index: 1140369 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.6025. Min Act: -0.0001

Data Index: 400221 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.5924. Min Act: -0.0001

Data Index: 1103034 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.5397. Min Act: -0.0001

Data Index: 240075 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.5306. Min Act: -0.0001

Data Index: 490801 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.4807. Min Act: -0.0001

Data Index: 952669 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.5068. Min Act: -0.0001

Data Index: 1300499 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.4314. Min Act: -0.0001

Data Index: 286642 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.3996. Min Act: -0.0001

Data Index: 99839 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.3933. Min Act: -0.0001

Data Index: 394849 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.4372. Min Act: -0.0001

Data Index: 193596 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.3807. Min Act: -0.0001

Data Index: 967151 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.4571. Min Act: -0.0001

Data Index: 767806 (C4 (Web Text))

Max Activating Token Index: 388