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

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

Neuron 5277 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.2858. Min Act: -0.0000

Data Index: 1472915 (Python Code)

Max Activating Token Index: 316

Text #1

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1432946 (Python Code)

Max Activating Token Index: 659

Text #2

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1473848 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.8685. Min Act: -0.0000

Data Index: 198221 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1416392 (Python Code)

Max Activating Token Index: 188

Text #5

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1599737 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1381546 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.7946. Min Act: -0.0000

Data Index: 986419 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1523766 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.7106. Min Act: -0.0000

Data Index: 482125 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.7065. Min Act: -0.0000

Data Index: 104476 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1421264 (Python Code)

Max Activating Token Index: 935

Text #12

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1600317 (Python Code)

Max Activating Token Index: 839

Text #13

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1312172 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.6316. Min Act: -0.0000

Data Index: 108462 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.6530. Min Act: -0.0000

Data Index: 25753 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1605535 (Python Code)

Max Activating Token Index: 151

Text #17

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1040104 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1324768 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.5843. Min Act: -0.0000

Data Index: 641486 (C4 (Web Text))

Max Activating Token Index: 938