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

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

Neuron 2644 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: 2.1017. Min Range: -2.1017

Max Act: 2.1017. Min Act: -0.0001

Data Index: 1270498 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.9418. Min Act: -0.0000

Data Index: 338867 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.8010. Min Act: -0.0000

Data Index: 1136204 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.5600. Min Act: -0.0000

Data Index: 1047919 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.5100. Min Act: -0.0001

Data Index: 983238 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.4410. Min Act: -0.0001

Data Index: 385847 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.4464. Min Act: -0.0000

Data Index: 1309328 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.4274. Min Act: -0.0001

Data Index: 780666 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.3709. Min Act: -0.0000

Data Index: 924816 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2735. Min Act: -0.0000

Data Index: 688574 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2329. Min Act: -0.0000

Data Index: 1338508 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2475. Min Act: -0.0000

Data Index: 385941 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2443. Min Act: -0.0001

Data Index: 388048 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2008. Min Act: -0.0000

Data Index: 372706 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.1722. Min Act: -0.0001

Data Index: 1326018 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.1301. Min Act: -0.0000

Data Index: 503469 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2058. Min Act: -0.0001

Data Index: 854487 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1223301 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1174872 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.1062. Min Act: -0.0000

Data Index: 208513 (C4 (Web Text))

Max Activating Token Index: 649