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

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

Neuron 1920 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.8348. Min Act: -0.0001

Data Index: 1665 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7890. Min Act: -0.0001

Data Index: 71705 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.8130. Min Act: -0.0001

Data Index: 144991 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7726. Min Act: -0.0001

Data Index: 330436 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7582. Min Act: -0.0001

Data Index: 158925 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7434. Min Act: -0.0001

Data Index: 1078679 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7083. Min Act: -0.0001

Data Index: 307634 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6520. Min Act: -0.0001

Data Index: 419473 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6056. Min Act: -0.0001

Data Index: 46075 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6384. Min Act: -0.0001

Data Index: 172764 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6515. Min Act: -0.0001

Data Index: 1051229 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6418. Min Act: -0.0001

Data Index: 1211310 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6260. Min Act: -0.0001

Data Index: 404678 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6495. Min Act: -0.0001

Data Index: 1240018 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6470. Min Act: -0.0001

Data Index: 494291 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6222. Min Act: -0.0001

Data Index: 1171083 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6336. Min Act: -0.0001

Data Index: 573799 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6339. Min Act: -0.0001

Data Index: 58008 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.5947. Min Act: -0.0001

Data Index: 499544 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6249. Min Act: -0.0001

Data Index: 178053 (C4 (Web Text))

Max Activating Token Index: 730