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

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

Neuron 5455 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.3859. Min Range: -8.3859

Max Act: 8.3859. Min Act: -0.0000

Data Index: 434672 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 8.3859. Min Range: -8.3859

Max Act: 7.8489. Min Act: -0.0000

Data Index: 384599 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 8.3859. Min Range: -8.3859

Max Act: 3.0299. Min Act: -0.0000

Data Index: 308809 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.5149. Min Act: -0.0000

Data Index: 240457 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.6408. Min Act: -0.0000

Data Index: 1313185 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.7494. Min Act: -0.0000

Data Index: 39607 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.6463. Min Act: -0.0000

Data Index: 492094 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.4820. Min Act: -0.0000

Data Index: 668364 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.4568. Min Act: -0.0000

Data Index: 23143 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.4269. Min Act: -0.0000

Data Index: 244060 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.2596. Min Act: -0.0000

Data Index: 1141816 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.3886. Min Act: -0.0000

Data Index: 452533 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.0899. Min Act: -0.0000

Data Index: 325211 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.1002. Min Act: -0.0000

Data Index: 451171 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 8.3859. Min Range: -8.3859

Max Act: 2.0274. Min Act: -0.0000

Data Index: 1102292 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 8.3859. Min Range: -8.3859

Max Act: 1.7847. Min Act: -0.0000

Data Index: 125234 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 8.3859. Min Range: -8.3859

Max Act: 1.7659. Min Act: -0.0000

Data Index: 886121 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 8.3859. Min Range: -8.3859

Max Act: 1.8099. Min Act: -0.0000

Data Index: 1314948 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 8.3859. Min Range: -8.3859

Max Act: 1.8084. Min Act: -0.0000

Data Index: 943466 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 8.3859. Min Range: -8.3859

Max Act: 1.8008. Min Act: 0.0000

Data Index: 132784 (C4 (Web Text))

Max Activating Token Index: 18