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

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

Neuron 3688 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.4130. Min Act: -0.0000

Data Index: 318478 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.4057. Min Act: -0.0001

Data Index: 9022 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3799. Min Act: -0.0000

Data Index: 230609 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3909. Min Act: -0.0000

Data Index: 53667 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3818. Min Act: -0.0000

Data Index: 999227 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3752. Min Act: -0.0000

Data Index: 299888 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1160792 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3614. Min Act: -0.0001

Data Index: 968612 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3575. Min Act: -0.0000

Data Index: 758358 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3445. Min Act: -0.0000

Data Index: 901942 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3670. Min Act: -0.0001

Data Index: 534726 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3522. Min Act: -0.0000

Data Index: 558891 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3479. Min Act: -0.0001

Data Index: 508906 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1155935 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1256299 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3283. Min Act: -0.0000

Data Index: 25900 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3337. Min Act: -0.0000

Data Index: 523295 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3339. Min Act: -0.0000

Data Index: 433539 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3330. Min Act: -0.0001

Data Index: 57309 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3328. Min Act: -0.0000

Data Index: 760023 (C4 (Web Text))

Max Activating Token Index: 537