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

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

Neuron 1324 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.7031. Min Act: -0.0001

Data Index: 433110 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.7156. Min Act: -0.0001

Data Index: 1209222 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6860. Min Act: -0.0001

Data Index: 480785 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6495. Min Act: -0.0001

Data Index: 45941 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6346. Min Act: -0.0001

Data Index: 583506 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6262. Min Act: -0.0001

Data Index: 495992 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6466. Min Act: -0.0001

Data Index: 181785 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6158. Min Act: -0.0001

Data Index: 338502 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6160. Min Act: -0.0001

Data Index: 1054660 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6268. Min Act: -0.0001

Data Index: 400631 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6253. Min Act: -0.0001

Data Index: 593218 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6238. Min Act: -0.0001

Data Index: 383263 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6251. Min Act: -0.0001

Data Index: 1331555 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6196. Min Act: -0.0001

Data Index: 440720 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6340. Min Act: -0.0001

Data Index: 159528 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.5922. Min Act: -0.0001

Data Index: 1199525 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6056. Min Act: -0.0001

Data Index: 1084212 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.5868. Min Act: -0.0001

Data Index: 796914 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6016. Min Act: -0.0001

Data Index: 228255 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.5847. Min Act: -0.0001

Data Index: 610072 (C4 (Web Text))

Max Activating Token Index: 958