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

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

Neuron 4605 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.8018. Min Act: -0.0000

Data Index: 420531 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.4872. Min Act: -0.0000

Data Index: 300704 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.2573. Min Act: -0.0000

Data Index: 1349579 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.9780. Min Act: -0.0000

Data Index: 1309393 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.8186. Min Act: -0.0000

Data Index: 881488 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.9151. Min Act: -0.0000

Data Index: 1038180 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.9983. Min Act: -0.0001

Data Index: 518413 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.7028. Min Act: -0.0000

Data Index: 937701 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.7764. Min Act: -0.0000

Data Index: 592091 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.8679. Min Act: -0.0000

Data Index: 191330 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.8557. Min Act: -0.0000

Data Index: 115169 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.6725. Min Act: -0.0000

Data Index: 280724 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.9292. Min Act: -0.0000

Data Index: 983880 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.7877. Min Act: -0.0000

Data Index: 343734 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.7712. Min Act: -0.0000

Data Index: 252208 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.1832. Min Act: -0.0000

Data Index: 202984 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.7959. Min Act: -0.0000

Data Index: 1045985 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.5345. Min Act: -0.0000

Data Index: 1037387 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.6280. Min Act: -0.0000

Data Index: 873574 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 3.8018. Min Range: -3.8018

Max Act: 2.5000. Min Act: -0.0000

Data Index: 1134413 (C4 (Web Text))

Max Activating Token Index: 17