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

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

Neuron 4543 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3245. Min Act: 0.0000

Data Index: 854171 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3257. Min Act: 0.0000

Data Index: 202437 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1241971 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2935. Min Act: 0.0000

Data Index: 111233 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2822. Min Act: 0.0000

Data Index: 1356923 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2831. Min Act: -0.0000

Data Index: 904236 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2671. Min Act: 0.0000

Data Index: 862535 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2785. Min Act: 0.0000

Data Index: 599471 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2919. Min Act: 0.0000

Data Index: 387169 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2735. Min Act: -0.0000

Data Index: 483160 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1172236 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2680. Min Act: 0.0000

Data Index: 396027 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2515. Min Act: 0.0000

Data Index: 716637 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2573. Min Act: 0.0000

Data Index: 753648 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2432. Min Act: -0.0000

Data Index: 651290 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1084399 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2454. Min Act: 0.0000

Data Index: 947724 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2280. Min Act: -0.0000

Data Index: 723966 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2363. Min Act: -0.0000

Data Index: 993971 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2393. Min Act: -0.0000

Data Index: 177837 (C4 (Web Text))

Max Activating Token Index: 471