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

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

Neuron 2483 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.8303. Min Act: -0.0001

Data Index: 632087 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.8358. Min Act: -0.0001

Data Index: 717605 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.7440. Min Act: -0.0001

Data Index: 1170981 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.7306. Min Act: -0.0001

Data Index: 384690 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.7053. Min Act: -0.0001

Data Index: 991573 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6923. Min Act: -0.0001

Data Index: 945468 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6612. Min Act: -0.0001

Data Index: 1332490 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6863. Min Act: -0.0001

Data Index: 666597 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6185. Min Act: -0.0001

Data Index: 829304 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6373. Min Act: -0.0001

Data Index: 990037 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6828. Min Act: -0.0000

Data Index: 583935 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6351. Min Act: -0.0001

Data Index: 925333 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6282. Min Act: -0.0001

Data Index: 1116425 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6257. Min Act: -0.0001

Data Index: 1283833 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6158. Min Act: -0.0000

Data Index: 910269 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6371. Min Act: -0.0000

Data Index: 582400 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.5907. Min Act: -0.0001

Data Index: 58883 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6057. Min Act: -0.0001

Data Index: 521240 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.5867. Min Act: -0.0001

Data Index: 533664 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.5826. Min Act: -0.0001

Data Index: 648868 (C4 (Web Text))

Max Activating Token Index: 933