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

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

Neuron 640 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.6337. Min Act: -0.0000

Data Index: 455125 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1101412 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4994. Min Act: -0.0000

Data Index: 879448 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4773. Min Act: -0.0000

Data Index: 554092 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4970. Min Act: -0.0000

Data Index: 728251 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4930. Min Act: -0.0001

Data Index: 35360 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4719. Min Act: -0.0000

Data Index: 26104 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4856. Min Act: -0.0000

Data Index: 988132 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4419. Min Act: -0.0000

Data Index: 276963 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1138083 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4356. Min Act: -0.0000

Data Index: 306280 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4466. Min Act: -0.0000

Data Index: 595474 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4427. Min Act: -0.0000

Data Index: 864440 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4442. Min Act: -0.0001

Data Index: 1354230 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1034594 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4344. Min Act: -0.0000

Data Index: 298158 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4288. Min Act: -0.0001

Data Index: 735493 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4212. Min Act: 0.0001

Data Index: 896030 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4165. Min Act: -0.0000

Data Index: 379259 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4185. Min Act: -0.0000

Data Index: 608386 (C4 (Web Text))

Max Activating Token Index: 145