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

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

Neuron 1736 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0804. Min Range: -4.0804

Max Act: 4.0804. Min Act: -0.0000

Data Index: 1165120 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.6266. Min Act: -0.0000

Data Index: 499502 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.2405. Min Act: -0.0000

Data Index: 265719 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.7229. Min Act: -0.0000

Data Index: 830071 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.4812. Min Act: -0.0000

Data Index: 1094346 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.3994. Min Act: -0.0000

Data Index: 1243294 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.2192. Min Act: -0.0000

Data Index: 52105 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.2117. Min Act: -0.0000

Data Index: 478697 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.1366. Min Act: -0.0000

Data Index: 14978 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.1138. Min Act: -0.0000

Data Index: 402022 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.2286. Min Act: -0.0000

Data Index: 29728 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.0711. Min Act: -0.0000

Data Index: 654757 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.1990. Min Act: -0.0000

Data Index: 534696 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.0644. Min Act: -0.0000

Data Index: 659827 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.1938. Min Act: -0.0000

Data Index: 1104543 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.1631. Min Act: -0.0000

Data Index: 177733 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.0156. Min Act: -0.0000

Data Index: 399890 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 4.0804. Min Range: -4.0804

Max Act: 2.8251. Min Act: -0.0000

Data Index: 775840 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 4.0804. Min Range: -4.0804

Max Act: 2.9830. Min Act: -0.0000

Data Index: 1014006 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 4.0804. Min Range: -4.0804

Max Act: 2.9587. Min Act: -0.0000

Data Index: 786914 (C4 (Web Text))

Max Activating Token Index: 346