Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 690 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.7361. Min Act: -0.0000

Data Index: 601975 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.6797. Min Act: -0.0000

Data Index: 943171 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1091324 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.6640. Min Act: -0.0000

Data Index: 991343 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.6239. Min Act: -0.0000

Data Index: 538698 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.6402. Min Act: -0.0000

Data Index: 715463 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1046659 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.5631. Min Act: -0.0000

Data Index: 998257 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1280653 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.5384. Min Act: -0.0000

Data Index: 353946 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1200411 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.5012. Min Act: -0.0000

Data Index: 461477 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.5200. Min Act: -0.0000

Data Index: 194316 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.5114. Min Act: -0.0000

Data Index: 858991 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1321311 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.5080. Min Act: -0.0000

Data Index: 417931 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.4758. Min Act: -0.0000

Data Index: 273806 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1068547 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.7361. Min Range: -0.7361

Max Act: 0.4630. Min Act: -0.0000

Data Index: 901334 (C4 (Web Text))

Max Activating Token Index: 69