Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 448 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.4870. Min Act: -0.0001

Data Index: 1112690 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.4808. Min Act: -0.0001

Data Index: 591836 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.5523. Min Act: -0.0001

Data Index: 938596 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.4921. Min Act: -0.0001

Data Index: 422829 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.4080. Min Act: -0.0001

Data Index: 503739 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.4213. Min Act: -0.0001

Data Index: 424456 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3839. Min Act: -0.0001

Data Index: 45496 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3334. Min Act: -0.0001

Data Index: 352128 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3351. Min Act: -0.0001

Data Index: 233082 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.4567. Min Act: -0.0001

Data Index: 243220 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3747. Min Act: -0.0001

Data Index: 1021565 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3578. Min Act: -0.0001

Data Index: 568850 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3019. Min Act: -0.0001

Data Index: 1310827 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3232. Min Act: -0.0001

Data Index: 899997 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3621. Min Act: -0.0001

Data Index: 878464 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.2799. Min Act: -0.0001

Data Index: 30204 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3576. Min Act: -0.0001

Data Index: 1209070 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.2766. Min Act: -0.0001

Data Index: 179253 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.2656. Min Act: -0.0001

Data Index: 1240689 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3850. Min Act: -0.0001

Data Index: 167687 (C4 (Web Text))

Max Activating Token Index: 779