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

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

Neuron 3417 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: 0.5755. Min Range: -0.5755

Max Act: 0.5755. Min Act: -0.0001

Data Index: 1300217 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.5492. Min Act: -0.0002

Data Index: 40669 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.5487. Min Act: -0.0002

Data Index: 442306 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4809. Min Act: -0.0001

Data Index: 193319 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4879. Min Act: -0.0001

Data Index: 585638 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.5306. Min Act: -0.0001

Data Index: 935795 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.5215. Min Act: -0.0002

Data Index: 82473 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4997. Min Act: -0.0001

Data Index: 791576 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.5459. Min Act: -0.0001

Data Index: 164033 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4885. Min Act: -0.0001

Data Index: 545777 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4521. Min Act: -0.0002

Data Index: 431335 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.5232. Min Act: -0.0001

Data Index: 988635 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4690. Min Act: -0.0001

Data Index: 277715 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4545. Min Act: -0.0001

Data Index: 1040242 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4678. Min Act: -0.0002

Data Index: 767102 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4313. Min Act: -0.0001

Data Index: 548549 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4260. Min Act: -0.0002

Data Index: 900528 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4278. Min Act: -0.0002

Data Index: 995922 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4588. Min Act: -0.0001

Data Index: 1053259 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.4480. Min Act: -0.0002

Data Index: 18809 (C4 (Web Text))

Max Activating Token Index: 791