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

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

Neuron 4559 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.5007. Min Act: -0.0003

Data Index: 1011292 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.3084. Min Act: -0.0003

Data Index: 1302072 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2912. Min Act: -0.0003

Data Index: 193554 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2808. Min Act: -0.0003

Data Index: 488024 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2802. Min Act: -0.0003

Data Index: 184048 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2674. Min Act: -0.0003

Data Index: 571684 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2618. Min Act: -0.0003

Data Index: 539356 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2660. Min Act: -0.0003

Data Index: 93485 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2640. Min Act: -0.0003

Data Index: 809777 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2732. Min Act: -0.0003

Data Index: 173933 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2449. Min Act: -0.0003

Data Index: 684917 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2527. Min Act: -0.0003

Data Index: 124784 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2332. Min Act: -0.0003

Data Index: 229306 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2424. Min Act: -0.0003

Data Index: 496264 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2493. Min Act: -0.0003

Data Index: 936975 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2464. Min Act: -0.0003

Data Index: 108745 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2449. Min Act: -0.0003

Data Index: 312995 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2377. Min Act: -0.0003

Data Index: 516415 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2419. Min Act: -0.0003

Data Index: 509264 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2251. Min Act: -0.0003

Data Index: 868081 (C4 (Web Text))

Max Activating Token Index: 477