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

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

Neuron 1789 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3788. Min Act: -0.0002

Data Index: 745051 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3753. Min Act: -0.0002

Data Index: 582483 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3596. Min Act: -0.0002

Data Index: 640730 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3627. Min Act: -0.0002

Data Index: 4080 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3463. Min Act: -0.0002

Data Index: 1107557 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3241. Min Act: -0.0002

Data Index: 388570 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3418. Min Act: -0.0002

Data Index: 108102 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3385. Min Act: -0.0002

Data Index: 349632 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3157. Min Act: -0.0002

Data Index: 401574 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3369. Min Act: -0.0002

Data Index: 614044 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2949. Min Act: -0.0002

Data Index: 57348 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3253. Min Act: -0.0002

Data Index: 277911 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3219. Min Act: -0.0002

Data Index: 706557 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3104. Min Act: -0.0002

Data Index: 1149593 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3189. Min Act: -0.0002

Data Index: 280346 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3131. Min Act: -0.0002

Data Index: 860292 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3066. Min Act: -0.0002

Data Index: 945799 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3490. Min Act: -0.0002

Data Index: 622928 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2919. Min Act: -0.0002

Data Index: 791624 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3158. Min Act: -0.0002

Data Index: 147513 (C4 (Web Text))

Max Activating Token Index: 765