Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2433 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6532. Min Act: -0.0000

Data Index: 792654 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6525. Min Act: -0.0001

Data Index: 287030 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6178. Min Act: -0.0001

Data Index: 1098200 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6370. Min Act: -0.0001

Data Index: 653129 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5787. Min Act: -0.0001

Data Index: 194483 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6327. Min Act: -0.0000

Data Index: 96049 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5656. Min Act: -0.0000

Data Index: 186371 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6022. Min Act: -0.0001

Data Index: 121789 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5940. Min Act: -0.0000

Data Index: 551111 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5647. Min Act: -0.0001

Data Index: 567855 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5250. Min Act: 0.0001

Data Index: 265247 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5602. Min Act: -0.0000

Data Index: 761853 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5442. Min Act: 0.0000

Data Index: 1251553 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5178. Min Act: 0.0001

Data Index: 501346 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6076. Min Act: -0.0001

Data Index: 180675 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5294. Min Act: -0.0001

Data Index: 511656 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5474. Min Act: -0.0001

Data Index: 1292458 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5571. Min Act: -0.0001

Data Index: 1145036 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5341. Min Act: 0.0001

Data Index: 875120 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5145. Min Act: -0.0001

Data Index: 373219 (C4 (Web Text))

Max Activating Token Index: 88