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

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

Neuron 3418 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: 0.6439. Min Range: -0.6439

Max Act: 0.6439. Min Act: -0.0000

Data Index: 292651 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1345457 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.5535. Min Act: -0.0000

Data Index: 192338 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.5306. Min Act: -0.0000

Data Index: 49508 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.5311. Min Act: -0.0000

Data Index: 695802 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.5233. Min Act: -0.0000

Data Index: 881170 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4961. Min Act: -0.0000

Data Index: 316837 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1038226 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4677. Min Act: -0.0000

Data Index: 736075 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4963. Min Act: -0.0000

Data Index: 588977 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4789. Min Act: -0.0000

Data Index: 890462 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4953. Min Act: -0.0000

Data Index: 983633 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1343835 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4878. Min Act: -0.0000

Data Index: 505736 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4862. Min Act: -0.0000

Data Index: 667003 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4674. Min Act: -0.0000

Data Index: 581777 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.5120. Min Act: -0.0000

Data Index: 229663 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4315. Min Act: -0.0000

Data Index: 969758 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1180157 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.6439. Min Range: -0.6439

Max Act: 0.4699. Min Act: -0.0000

Data Index: 983691 (C4 (Web Text))

Max Activating Token Index: 385