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

Dataset: The Pile

Neuron 1249 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.2150. Min Act: -0.0000

Data Index: 523332 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1310597 (The Pile)

Max Activating Token Index: 800

Text #2

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.3445. Min Act: -0.0000

Data Index: 596124 (The Pile)

Max Activating Token Index: 918

Text #3

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.7348. Min Act: -0.0000

Data Index: 418452 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.1491. Min Act: -0.0000

Data Index: 449753 (The Pile)

Max Activating Token Index: 565

Text #5

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0393. Min Act: -0.0000

Data Index: 261802 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.1020. Min Act: -0.0000

Data Index: 306778 (The Pile)

Max Activating Token Index: 3

Text #7

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1133547 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1068348 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1522275 (The Pile)

Max Activating Token Index: 685

Text #10

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1355417 (The Pile)

Max Activating Token Index: 942

Text #11

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0924. Min Act: -0.0000

Data Index: 677397 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9421. Min Act: -0.0000

Data Index: 140122 (The Pile)

Max Activating Token Index: 984

Text #13

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1836864 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9823. Min Act: -0.0000

Data Index: 855831 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9531. Min Act: -0.0000

Data Index: 153281 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1596878 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1178352 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8485. Min Act: -0.0000

Data Index: 960247 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0464. Min Act: -0.0000

Data Index: 1880317 (The Pile)

Max Activating Token Index: 864