Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 65 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.4306. Min Act: -0.0001

Data Index: 282440 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.4033. Min Act: -0.0001

Data Index: 658293 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3883. Min Act: -0.0001

Data Index: 724948 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1286689 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3561. Min Act: -0.0001

Data Index: 897686 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3894. Min Act: -0.0001

Data Index: 13316 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3382. Min Act: -0.0001

Data Index: 219176 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3631. Min Act: -0.0001

Data Index: 782992 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3370. Min Act: -0.0001

Data Index: 63914 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3515. Min Act: -0.0001

Data Index: 480755 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3283. Min Act: -0.0001

Data Index: 806013 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3207. Min Act: -0.0001

Data Index: 1064909 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3105. Min Act: -0.0001

Data Index: 1237273 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3438. Min Act: -0.0001

Data Index: 294387 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3011. Min Act: -0.0001

Data Index: 1043568 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3000. Min Act: -0.0001

Data Index: 69208 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2982. Min Act: -0.0001

Data Index: 548295 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2672. Min Act: -0.0001

Data Index: 1276635 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3042. Min Act: -0.0001

Data Index: 60350 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3116. Min Act: -0.0001

Data Index: 665471 (C4 (Web Text))

Max Activating Token Index: 527