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

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

Neuron 3355 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3908. Min Act: -0.0000

Data Index: 623544 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3814. Min Act: -0.0000

Data Index: 517871 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3572. Min Act: -0.0000

Data Index: 596636 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1025157 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3085. Min Act: -0.0001

Data Index: 116400 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3096. Min Act: -0.0000

Data Index: 208378 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2879. Min Act: 0.0000

Data Index: 820210 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2647. Min Act: -0.0000

Data Index: 615468 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2736. Min Act: -0.0000

Data Index: 356512 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2670. Min Act: -0.0000

Data Index: 69314 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2620. Min Act: -0.0000

Data Index: 920371 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2589. Min Act: -0.0000

Data Index: 761294 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1157194 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1030144 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1131454 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2425. Min Act: -0.0000

Data Index: 395687 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2241. Min Act: -0.0000

Data Index: 645492 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2274. Min Act: -0.0000

Data Index: 543154 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2392. Min Act: -0.0000

Data Index: 259716 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2264. Min Act: -0.0000

Data Index: 841531 (C4 (Web Text))

Max Activating Token Index: 1003