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

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

Neuron 82 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: 12.1499. Min Range: -12.1499

Max Act: 12.1499. Min Act: -0.0001

Data Index: 185329 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.8773. Min Act: -0.0001

Data Index: 181854 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.6877. Min Act: -0.0001

Data Index: 36746 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.9094. Min Act: -0.0001

Data Index: 650100 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.6349. Min Act: -0.0001

Data Index: 195663 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.8913. Min Act: -0.0001

Data Index: 1180072 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.7791. Min Act: -0.0001

Data Index: 675092 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.7506. Min Act: -0.0001

Data Index: 551429 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.6294. Min Act: -0.0001

Data Index: 348817 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.4960. Min Act: -0.0001

Data Index: 1083710 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.5715. Min Act: -0.0001

Data Index: 240423 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.6345. Min Act: -0.0001

Data Index: 363171 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.6364. Min Act: -0.0001

Data Index: 1023557 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.5191. Min Act: -0.0001

Data Index: 228192 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.6757. Min Act: -0.0001

Data Index: 966066 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.6670. Min Act: -0.0001

Data Index: 774712 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.4119. Min Act: -0.0001

Data Index: 84344 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.3005. Min Act: -0.0001

Data Index: 1214056 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.3884. Min Act: -0.0001

Data Index: 900039 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 12.1499. Min Range: -12.1499

Max Act: 11.3566. Min Act: -0.0001

Data Index: 435926 (C4 (Web Text))

Max Activating Token Index: 200