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

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

Neuron 2686 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.6773. Min Act: -0.0001

Data Index: 905682 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1129172 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.6290. Min Act: -0.0000

Data Index: 903969 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5833. Min Act: -0.0001

Data Index: 977889 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1146938 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5691. Min Act: 0.0001

Data Index: 1242564 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1036111 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.4706. Min Act: -0.0001

Data Index: 430420 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.4615. Min Act: -0.0000

Data Index: 198360 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1334450 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.4211. Min Act: -0.0001

Data Index: 273048 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1021763 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.4070. Min Act: -0.0001

Data Index: 484257 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.4034. Min Act: -0.0001

Data Index: 650651 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.3655. Min Act: -0.0000

Data Index: 622268 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.3724. Min Act: -0.0000

Data Index: 93442 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.3689. Min Act: -0.0001

Data Index: 220389 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.3535. Min Act: -0.0001

Data Index: 652121 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.3243. Min Act: -0.0001

Data Index: 644867 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.3343. Min Act: -0.0000

Data Index: 314173 (C4 (Web Text))

Max Activating Token Index: 43