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

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

Neuron 1395 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.5160. Min Act: -0.0000

Data Index: 990768 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4807. Min Act: 0.0000

Data Index: 609057 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4324. Min Act: 0.0000

Data Index: 527677 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4374. Min Act: -0.0000

Data Index: 919098 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4301. Min Act: -0.0000

Data Index: 313190 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4251. Min Act: 0.0000

Data Index: 1256135 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4222. Min Act: -0.0000

Data Index: 749811 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1317686 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4037. Min Act: -0.0000

Data Index: 266783 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3973. Min Act: -0.0000

Data Index: 291106 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3841. Min Act: 0.0000

Data Index: 1275427 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3645. Min Act: -0.0000

Data Index: 465218 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3607. Min Act: -0.0000

Data Index: 504311 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3693. Min Act: -0.0000

Data Index: 332921 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3535. Min Act: -0.0001

Data Index: 1164894 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3520. Min Act: 0.0000

Data Index: 1004496 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3565. Min Act: 0.0000

Data Index: 313509 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3327. Min Act: -0.0000

Data Index: 126123 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3477. Min Act: -0.0000

Data Index: 158848 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3408. Min Act: -0.0000

Data Index: 385594 (C4 (Web Text))

Max Activating Token Index: 47