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

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

Neuron 672 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: 0.7414. Min Range: -0.7414

Max Act: 0.7414. Min Act: -0.0000

Data Index: 69069 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1160569 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5875. Min Act: -0.0000

Data Index: 754192 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1122829 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1281003 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5758. Min Act: -0.0000

Data Index: 917054 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5447. Min Act: -0.0000

Data Index: 176558 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5144. Min Act: -0.0000

Data Index: 910816 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1063996 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5528. Min Act: -0.0000

Data Index: 75920 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5302. Min Act: -0.0000

Data Index: 419132 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5649. Min Act: -0.0000

Data Index: 652124 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5243. Min Act: -0.0000

Data Index: 289300 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5339. Min Act: -0.0000

Data Index: 856159 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5485. Min Act: -0.0000

Data Index: 889285 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5316. Min Act: -0.0000

Data Index: 994482 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1333091 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6023. Min Act: -0.0000

Data Index: 329184 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1335936 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1057181 (C4 (Web Text))

Max Activating Token Index: 491