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

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

Neuron 3780 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9716. Min Act: -0.0001

Data Index: 89079 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8489. Min Act: -0.0000

Data Index: 249990 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8554. Min Act: -0.0001

Data Index: 711542 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7716. Min Act: -0.0001

Data Index: 91686 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7913. Min Act: -0.0001

Data Index: 396035 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7910. Min Act: -0.0001

Data Index: 794910 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7952. Min Act: -0.0000

Data Index: 718425 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7835. Min Act: -0.0001

Data Index: 509959 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1299944 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7624. Min Act: -0.0000

Data Index: 443968 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7303. Min Act: -0.0000

Data Index: 267252 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7983. Min Act: -0.0001

Data Index: 1195955 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7272. Min Act: -0.0001

Data Index: 427091 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7397. Min Act: -0.0001

Data Index: 1314571 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7356. Min Act: -0.0001

Data Index: 1285869 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7099. Min Act: -0.0001

Data Index: 630801 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1232170 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7268. Min Act: -0.0000

Data Index: 594800 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7042. Min Act: -0.0000

Data Index: 257419 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7178. Min Act: -0.0000

Data Index: 997644 (C4 (Web Text))

Max Activating Token Index: 453