Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4242 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.8329. Min Act: -0.0000

Data Index: 794002 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.4927. Min Act: -0.0000

Data Index: 1147457 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.4142. Min Act: -0.0000

Data Index: 957259 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.3544. Min Act: -0.0000

Data Index: 693690 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.1179. Min Act: -0.0000

Data Index: 354438 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.4570. Min Act: -0.0000

Data Index: 1086732 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.0533. Min Act: -0.0000

Data Index: 414001 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.2758. Min Act: -0.0000

Data Index: 16889 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.2136. Min Act: -0.0000

Data Index: 519360 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.1003. Min Act: -0.0000

Data Index: 257023 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.1693. Min Act: -0.0000

Data Index: 979961 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.1956. Min Act: -0.0000

Data Index: 166235 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.0365. Min Act: -0.0000

Data Index: 1330437 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.1383. Min Act: -0.0000

Data Index: 134546 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.1234. Min Act: -0.0000

Data Index: 485689 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.0034. Min Act: -0.0000

Data Index: 1074318 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.2207. Min Act: -0.0000

Data Index: 245869 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 2.8329. Min Range: -2.8329

Max Act: 2.0813. Min Act: -0.0000

Data Index: 81326 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 2.8329. Min Range: -2.8329

Max Act: 1.9151. Min Act: -0.0000

Data Index: 667250 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 2.8329. Min Range: -2.8329

Max Act: 1.9124. Min Act: -0.0000

Data Index: 626179 (C4 (Web Text))

Max Activating Token Index: 893