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

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

Neuron 2756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.5342. Min Act: -0.0001

Data Index: 586439 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1314435 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.5234. Min Act: -0.0000

Data Index: 549519 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4789. Min Act: -0.0000

Data Index: 402095 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4564. Min Act: -0.0000

Data Index: 948533 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4403. Min Act: -0.0000

Data Index: 542906 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4788. Min Act: -0.0001

Data Index: 757038 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1055685 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4323. Min Act: -0.0000

Data Index: 635215 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4170. Min Act: -0.0001

Data Index: 62138 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4274. Min Act: -0.0001

Data Index: 1336596 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1337140 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3836. Min Act: -0.0000

Data Index: 301311 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4268. Min Act: -0.0001

Data Index: 88455 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1324624 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4153. Min Act: -0.0001

Data Index: 190770 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4137. Min Act: -0.0000

Data Index: 542124 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4042. Min Act: -0.0001

Data Index: 325315 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3977. Min Act: -0.0000

Data Index: 622825 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3995. Min Act: -0.0000

Data Index: 899367 (C4 (Web Text))

Max Activating Token Index: 810