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

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

Neuron 2635 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.4342. Min Act: -0.0001

Data Index: 623947 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.3593. Min Act: -0.0001

Data Index: 78917 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.3118. Min Act: -0.0001

Data Index: 473917 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.3579. Min Act: -0.0001

Data Index: 273380 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.2998. Min Act: -0.0001

Data Index: 1060852 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.1511. Min Act: -0.0001

Data Index: 667815 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.1332. Min Act: -0.0001

Data Index: 95418 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.1703. Min Act: -0.0001

Data Index: 549975 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.2642. Min Act: -0.0002

Data Index: 361659 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0221. Min Act: -0.0002

Data Index: 11890 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.1563. Min Act: -0.0001

Data Index: 739877 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.1276. Min Act: -0.0001

Data Index: 1354346 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 1.4342. Min Range: -1.4342

Max Act: 0.9852. Min Act: -0.0001

Data Index: 58251 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0640. Min Act: -0.0001

Data Index: 550533 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0151. Min Act: -0.0001

Data Index: 790252 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.4342. Min Range: -1.4342

Max Act: 0.9273. Min Act: -0.0002

Data Index: 838579 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0083. Min Act: -0.0001

Data Index: 607833 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0067. Min Act: -0.0001

Data Index: 760560 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0297. Min Act: -0.0001

Data Index: 716587 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0238. Min Act: -0.0001

Data Index: 803554 (C4 (Web Text))

Max Activating Token Index: 437