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

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

Neuron 3699 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: 0.9207. Min Range: -0.9207

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1275275 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.9207. Min Act: -0.0000

Data Index: 162640 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7449. Min Act: -0.0001

Data Index: 856749 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6566. Min Act: -0.0001

Data Index: 1336510 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6316. Min Act: -0.0001

Data Index: 619955 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6077. Min Act: -0.0001

Data Index: 1259286 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5715. Min Act: -0.0001

Data Index: 154581 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1295225 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5373. Min Act: -0.0000

Data Index: 287752 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1240183 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5515. Min Act: -0.0001

Data Index: 398702 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1277280 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.4966. Min Act: -0.0001

Data Index: 392090 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5308. Min Act: -0.0001

Data Index: 851837 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5361. Min Act: -0.0000

Data Index: 438085 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5057. Min Act: -0.0001

Data Index: 358102 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.4863. Min Act: -0.0000

Data Index: 440024 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.4852. Min Act: -0.0000

Data Index: 951583 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5161. Min Act: -0.0000

Data Index: 684386 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.5141. Min Act: -0.0001

Data Index: 38312 (C4 (Web Text))

Max Activating Token Index: 895