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

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

Neuron 3838 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: 0.5469. Min Range: -0.5469

Max Act: 0.5469. Min Act: -0.0000

Data Index: 338585 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.3228. Min Act: -0.0000

Data Index: 318133 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.3046. Min Act: -0.0000

Data Index: 420327 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.3140. Min Act: -0.0001

Data Index: 344501 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.3229. Min Act: 0.0001

Data Index: 889431 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1023029 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2696. Min Act: -0.0000

Data Index: 681487 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1140734 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2690. Min Act: -0.0000

Data Index: 761727 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2680. Min Act: 0.0000

Data Index: 69509 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1347186 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2497. Min Act: -0.0001

Data Index: 591407 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2582. Min Act: -0.0000

Data Index: 280777 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2548. Min Act: -0.0000

Data Index: 516559 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2476. Min Act: -0.0001

Data Index: 105112 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2541. Min Act: -0.0001

Data Index: 927759 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2365. Min Act: -0.0000

Data Index: 338223 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1333650 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2308. Min Act: -0.0001

Data Index: 973567 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.2392. Min Act: -0.0000

Data Index: 130672 (C4 (Web Text))

Max Activating Token Index: 536