Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3452 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0670. Min Range: -1.0670

Max Act: 1.0670. Min Act: -0.0000

Data Index: 566959 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.9736. Min Act: 0.0003

Data Index: 13453 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.9094. Min Act: 0.0001

Data Index: 202952 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.9035. Min Act: -0.0000

Data Index: 1041593 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8344. Min Act: 0.0000

Data Index: 133532 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8536. Min Act: -0.0000

Data Index: 614844 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.9028. Min Act: -0.0000

Data Index: 316916 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8095. Min Act: -0.0000

Data Index: 493153 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8033. Min Act: 0.0000

Data Index: 193390 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1151581 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8193. Min Act: -0.0000

Data Index: 640551 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7885. Min Act: -0.0000

Data Index: 715164 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8194. Min Act: -0.0000

Data Index: 109895 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7902. Min Act: -0.0000

Data Index: 365631 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8567. Min Act: -0.0000

Data Index: 571155 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7826. Min Act: -0.0000

Data Index: 328735 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7552. Min Act: -0.0000

Data Index: 744533 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7550. Min Act: -0.0000

Data Index: 278675 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1283142 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7499. Min Act: -0.0000

Data Index: 357872 (C4 (Web Text))

Max Activating Token Index: 100