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

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

Neuron 2640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.4450. Min Act: -0.0000

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3953. Min Act: -0.0000

Data Index: 628157 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3931. Min Act: -0.0000

Data Index: 884769 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3803. Min Act: -0.0000

Data Index: 955438 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3833. Min Act: -0.0000

Data Index: 113167 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3492. Min Act: -0.0001

Data Index: 406200 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3488. Min Act: -0.0000

Data Index: 662205 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3721. Min Act: -0.0000

Data Index: 402793 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3540. Min Act: -0.0000

Data Index: 734061 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3517. Min Act: -0.0000

Data Index: 144564 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3597. Min Act: -0.0000

Data Index: 128308 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3481. Min Act: -0.0000

Data Index: 110253 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3296. Min Act: -0.0000

Data Index: 622181 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1069949 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3363. Min Act: -0.0000

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3264. Min Act: -0.0000

Data Index: 920473 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3318. Min Act: -0.0000

Data Index: 283753 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3210. Min Act: -0.0000

Data Index: 289432 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3297. Min Act: -0.0001

Data Index: 1184552 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3269. Min Act: -0.0000

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 309