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

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

Neuron 3423 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.7265. Min Act: 0.0000

Data Index: 497508 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.7477. Min Act: -0.0000

Data Index: 748394 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.7300. Min Act: -0.0000

Data Index: 299655 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6774. Min Act: -0.0000

Data Index: 414188 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1000012 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.7081. Min Act: -0.0000

Data Index: 251003 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1169605 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6950. Min Act: -0.0000

Data Index: 719721 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6523. Min Act: -0.0000

Data Index: 790595 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1264538 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6905. Min Act: -0.0000

Data Index: 970651 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6316. Min Act: -0.0000

Data Index: 684501 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6175. Min Act: -0.0000

Data Index: 603444 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6789. Min Act: -0.0000

Data Index: 669290 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6202. Min Act: -0.0000

Data Index: 507445 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6423. Min Act: -0.0000

Data Index: 295414 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6891. Min Act: -0.0000

Data Index: 606278 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1166448 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.5607. Min Act: -0.0000

Data Index: 832120 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6477. Min Act: -0.0000

Data Index: 238139 (C4 (Web Text))

Max Activating Token Index: 66