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

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

Neuron 3870 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3311. Min Range: -3.3311

Max Act: 3.3311. Min Act: -0.0000

Data Index: 954229 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.3311. Min Range: -3.3311

Max Act: 2.3373. Min Act: -0.0000

Data Index: 722309 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 3.3311. Min Range: -3.3311

Max Act: 2.4448. Min Act: -0.0000

Data Index: 775947 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 3.3311. Min Range: -3.3311

Max Act: 2.0925. Min Act: -0.0000

Data Index: 817379 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 3.3311. Min Range: -3.3311

Max Act: 2.3039. Min Act: -0.0000

Data Index: 1225636 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 3.3311. Min Range: -3.3311

Max Act: 2.2542. Min Act: -0.0000

Data Index: 1327174 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.8428. Min Act: -0.0000

Data Index: 1166479 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.9544. Min Act: -0.0000

Data Index: 275077 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.8634. Min Act: -0.0000

Data Index: 317794 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.6713. Min Act: -0.0000

Data Index: 319971 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.8939. Min Act: -0.0000

Data Index: 589296 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.7735. Min Act: -0.0000

Data Index: 135517 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.7518. Min Act: -0.0000

Data Index: 1308239 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.7967. Min Act: -0.0000

Data Index: 921620 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.6921. Min Act: -0.0000

Data Index: 239108 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.7799. Min Act: -0.0000

Data Index: 216299 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.7824. Min Act: -0.0000

Data Index: 526376 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1184415 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.4635. Min Act: -0.0000

Data Index: 86498 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 3.3311. Min Range: -3.3311

Max Act: 1.5011. Min Act: -0.0000

Data Index: 1278086 (C4 (Web Text))

Max Activating Token Index: 816