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

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

Neuron 2295 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1488. Min Range: -3.1488

Max Act: 3.1488. Min Act: -0.0000

Data Index: 379334 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 3.1488. Min Range: -3.1488

Max Act: 3.0498. Min Act: -0.0000

Data Index: 1100970 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.3701. Min Act: -0.0000

Data Index: 549748 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.3282. Min Act: -0.0000

Data Index: 139957 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.4184. Min Act: -0.0000

Data Index: 593317 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.2519. Min Act: -0.0000

Data Index: 841855 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.2293. Min Act: -0.0000

Data Index: 1354944 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.2012. Min Act: -0.0000

Data Index: 919667 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.1934. Min Act: -0.0000

Data Index: 69807 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.3988. Min Act: -0.0000

Data Index: 965224 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.3752. Min Act: -0.0000

Data Index: 1188542 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.2567. Min Act: -0.0000

Data Index: 37734 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.2275. Min Act: -0.0000

Data Index: 859808 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.2402. Min Act: -0.0000

Data Index: 1110070 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.2232. Min Act: -0.0000

Data Index: 1098520 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.2292. Min Act: -0.0000

Data Index: 1277711 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.2145. Min Act: -0.0000

Data Index: 1066117 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.0943. Min Act: -0.0000

Data Index: 499254 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.1636. Min Act: -0.0000

Data Index: 135566 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 3.1488. Min Range: -3.1488

Max Act: 2.1684. Min Act: -0.0000

Data Index: 137925 (C4 (Web Text))

Max Activating Token Index: 504