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

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

Neuron 4201 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0227. Min Range: -3.0227

Max Act: 3.0227. Min Act: -0.0000

Data Index: 10759 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 3.0227. Min Range: -3.0227

Max Act: 3.0092. Min Act: -0.0000

Data Index: 862123 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.9649. Min Act: -0.0000

Data Index: 534940 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.9465. Min Act: -0.0000

Data Index: 218262 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.7401. Min Act: -0.0000

Data Index: 452987 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.7765. Min Act: -0.0000

Data Index: 223638 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.7570. Min Act: -0.0000

Data Index: 662269 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.7305. Min Act: -0.0000

Data Index: 778291 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.5968. Min Act: -0.0000

Data Index: 886394 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.8414. Min Act: -0.0000

Data Index: 630133 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.5511. Min Act: -0.0000

Data Index: 199296 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.6626. Min Act: -0.0000

Data Index: 1233558 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.6524. Min Act: -0.0000

Data Index: 1341944 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.5872. Min Act: -0.0000

Data Index: 710224 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.5818. Min Act: -0.0000

Data Index: 468317 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.5816. Min Act: -0.0000

Data Index: 487717 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.5707. Min Act: -0.0000

Data Index: 1222464 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.5521. Min Act: -0.0000

Data Index: 941856 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.5594. Min Act: -0.0000

Data Index: 1304347 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 3.0227. Min Range: -3.0227

Max Act: 2.5560. Min Act: -0.0000

Data Index: 50979 (C4 (Web Text))

Max Activating Token Index: 202