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

Dataset: The Pile

Neuron 2196 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0000

Data Index: 1749033 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0462. Min Act: -0.0000

Data Index: 84351 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1757192 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0451. Min Act: 0.0000

Data Index: 1267984 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1299523 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0450. Min Act: 0.0000

Data Index: 1196901 (The Pile)

Max Activating Token Index: 3

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0448. Min Act: -0.0000

Data Index: 1395020 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0447. Min Act: -0.0000

Data Index: 1540827 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1526911 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1777391 (The Pile)

Max Activating Token Index: 6

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1233891 (The Pile)

Max Activating Token Index: 3

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1184100 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0428. Min Act: -0.0000

Data Index: 373289 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1149596 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0441. Min Act: 0.0000

Data Index: 162280 (The Pile)

Max Activating Token Index: 10

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0441. Min Act: -0.0000

Data Index: 99063 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1339512 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0439. Min Act: -0.0000

Data Index: 468390 (The Pile)

Max Activating Token Index: 7

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0439. Min Act: -0.0000

Data Index: 140938 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1385193 (The Pile)

Max Activating Token Index: 6