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

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

Neuron 3352 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3673. Min Act: -0.0000

Data Index: 524540 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1142610 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1179678 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1014897 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3592. Min Act: -0.0000

Data Index: 667234 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1619273 (Python Code)

Max Activating Token Index: 426

Text #6

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1165608 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2970. Min Act: -0.0000

Data Index: 54079 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1297981 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1378711 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1163624 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2673. Min Act: -0.0000

Data Index: 453950 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1394168 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2446. Min Act: -0.0000

Data Index: 612243 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2367. Min Act: -0.0000

Data Index: 45153 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2128. Min Act: -0.0000

Data Index: 666332 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1493335 (Python Code)

Max Activating Token Index: 171

Text #18

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1556220 (Python Code)

Max Activating Token Index: 240

Text #19

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.1978. Min Act: -0.0000

Data Index: 647853 (C4 (Web Text))

Max Activating Token Index: 880