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

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

Neuron 71 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0861. Min Range: -1.0861

Max Act: 1.0861. Min Act: -0.0000

Data Index: 1310264 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.0861. Min Range: -1.0861

Max Act: 1.0354. Min Act: -0.0000

Data Index: 548323 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.0861. Min Range: -1.0861

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1145337 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 1.0861. Min Range: -1.0861

Max Act: 1.0555. Min Act: -0.0000

Data Index: 69300 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 1.0861. Min Range: -1.0861

Max Act: 1.0024. Min Act: -0.0000

Data Index: 279995 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1120558 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 1.0861. Min Range: -1.0861

Max Act: 1.0392. Min Act: -0.0000

Data Index: 555748 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9428. Min Act: -0.0000

Data Index: 877525 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 1.0861. Min Range: -1.0861

Max Act: 1.0002. Min Act: -0.0000

Data Index: 199708 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9394. Min Act: -0.0000

Data Index: 509179 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9937. Min Act: -0.0000

Data Index: 881898 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9881. Min Act: -0.0000

Data Index: 899659 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1184527 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9753. Min Act: -0.0000

Data Index: 164058 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9156. Min Act: -0.0000

Data Index: 155258 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9964. Min Act: -0.0000

Data Index: 466090 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9576. Min Act: -0.0000

Data Index: 206056 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9510. Min Act: -0.0000

Data Index: 651802 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9813. Min Act: -0.0000

Data Index: 147049 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9533. Min Act: -0.0000

Data Index: 51191 (C4 (Web Text))

Max Activating Token Index: 619