Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3401 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.3048. Min Act: -0.0000

Data Index: 686088 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.3101. Min Act: -0.0000

Data Index: 972767 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.3019. Min Act: -0.0000

Data Index: 426038 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1348524 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2789. Min Act: -0.0000

Data Index: 768 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1275795 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2749. Min Act: -0.0000

Data Index: 593419 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1073437 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1279099 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2326. Min Act: -0.0000

Data Index: 520439 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1294629 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2359. Min Act: -0.0000

Data Index: 66848 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1224549 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1339010 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2383. Min Act: -0.0000

Data Index: 695317 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2524. Min Act: -0.0000

Data Index: 965915 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2293. Min Act: -0.0000

Data Index: 604122 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2289. Min Act: -0.0000

Data Index: 662291 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2355. Min Act: -0.0000

Data Index: 846418 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.3101. Min Range: -0.3101

Max Act: 0.2379. Min Act: -0.0000

Data Index: 847548 (C4 (Web Text))

Max Activating Token Index: 578