Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 494 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8350. Min Act: -0.0000

Data Index: 1161213 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.1411. Min Act: -0.0000

Data Index: 1146516 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.1133. Min Act: -0.0000

Data Index: 1304733 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.0880. Min Act: -0.0000

Data Index: 1271343 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.2874. Min Act: -0.0000

Data Index: 404056 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.6470. Min Act: -0.0000

Data Index: 227771 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.6612. Min Act: -0.0000

Data Index: 1334366 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.3613. Min Act: -0.0000

Data Index: 404504 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.4493. Min Act: -0.0000

Data Index: 876917 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.1994. Min Act: -0.0000

Data Index: 599469 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.2812. Min Act: -0.0000

Data Index: 382025 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.3960. Min Act: -0.0000

Data Index: 719901 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.3565. Min Act: -0.0000

Data Index: 976854 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.3011. Min Act: -0.0000

Data Index: 161950 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.1116. Min Act: -0.0000

Data Index: 98647 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 3.8350. Min Range: -3.8350

Max Act: 1.9901. Min Act: -0.0000

Data Index: 350611 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.0764. Min Act: -0.0000

Data Index: 919646 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.1698. Min Act: -0.0000

Data Index: 1084553 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 3.8350. Min Range: -3.8350

Max Act: 2.1259. Min Act: -0.0000

Data Index: 51081 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 3.8350. Min Range: -3.8350

Max Act: 1.9521. Min Act: -0.0000

Data Index: 1077712 (C4 (Web Text))

Max Activating Token Index: 837