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

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

Neuron 2966 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1145. Min Range: -1.1145

Max Act: 1.1145. Min Act: -0.0000

Data Index: 1074736 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9778. Min Act: -0.0000

Data Index: 487671 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1307289 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.8433. Min Act: -0.0000

Data Index: 766902 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1305879 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7349. Min Act: -0.0001

Data Index: 98732 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7072. Min Act: -0.0000

Data Index: 154048 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7070. Min Act: -0.0000

Data Index: 340228 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7347. Min Act: -0.0001

Data Index: 188739 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7691. Min Act: -0.0000

Data Index: 515221 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1341459 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7153. Min Act: -0.0000

Data Index: 662205 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7584. Min Act: -0.0000

Data Index: 132456 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7735. Min Act: -0.0000

Data Index: 962099 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6980. Min Act: -0.0001

Data Index: 426693 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6815. Min Act: -0.0000

Data Index: 637036 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6770. Min Act: -0.0000

Data Index: 5360 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6607. Min Act: -0.0000

Data Index: 380061 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6584. Min Act: -0.0000

Data Index: 946055 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6520. Min Act: -0.0001

Data Index: 138253 (C4 (Web Text))

Max Activating Token Index: 226