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

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

Neuron 3323 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.7145. Min Act: -0.0001

Data Index: 449428 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.2775. Min Act: -0.0001

Data Index: 441720 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.3212. Min Act: -0.0001

Data Index: 24556 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.2318. Min Act: -0.0001

Data Index: 25532 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1519. Min Act: -0.0001

Data Index: 1034380 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1998. Min Act: -0.0001

Data Index: 769472 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1869. Min Act: -0.0001

Data Index: 775568 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.2238. Min Act: -0.0001

Data Index: 684614 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1771. Min Act: -0.0001

Data Index: 543167 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1653. Min Act: -0.0001

Data Index: 1069752 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1511. Min Act: -0.0001

Data Index: 1147075 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1103. Min Act: -0.0001

Data Index: 148452 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1404. Min Act: -0.0001

Data Index: 1246645 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1706. Min Act: -0.0001

Data Index: 603201 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1396. Min Act: -0.0001

Data Index: 584728 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1320. Min Act: -0.0001

Data Index: 308564 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1041. Min Act: -0.0001

Data Index: 214768 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1290. Min Act: -0.0001

Data Index: 1356419 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1140. Min Act: -0.0001

Data Index: 1006706 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.0733. Min Act: -0.0001

Data Index: 449421 (C4 (Web Text))

Max Activating Token Index: 959