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

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

Neuron 752 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.2890. Min Act: -0.0000

Data Index: 1206360 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.2810. Min Act: -0.0000

Data Index: 1091628 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.2669. Min Act: -0.0000

Data Index: 333348 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.2551. Min Act: -0.0000

Data Index: 695947 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.1721. Min Act: -0.0000

Data Index: 166620 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0337. Min Act: -0.0000

Data Index: 330079 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0227. Min Act: 0.0000

Data Index: 798283 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0941. Min Act: -0.0000

Data Index: 784319 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0831. Min Act: -0.0000

Data Index: 746727 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0522. Min Act: -0.0000

Data Index: 308979 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9274. Min Act: -0.0000

Data Index: 877640 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.5874. Min Act: -0.0000

Data Index: 533267 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.2957. Min Act: -0.0000

Data Index: 584035 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 2.2890. Min Range: -2.2890

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1297139 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 2.2890. Min Range: -2.2890

Max Act: 0.9852. Min Act: -0.0000

Data Index: 869112 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 2.2890. Min Range: -2.2890

Max Act: 0.8996. Min Act: -0.0000

Data Index: 1236705 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 2.2890. Min Range: -2.2890

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1113362 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 2.2890. Min Range: -2.2890

Max Act: 0.8521. Min Act: -0.0000

Data Index: 81797 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 2.2890. Min Range: -2.2890

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1454275 (Python Code)

Max Activating Token Index: 988

Text #19

Max Range: 2.2890. Min Range: -2.2890

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1258646 (C4 (Web Text))

Max Activating Token Index: 652