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

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

Neuron 2952 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: 0.5445. Min Range: -0.5445

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1055847 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1269870 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1291732 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4873. Min Act: -0.0000

Data Index: 109729 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4769. Min Act: -0.0000

Data Index: 126192 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1166552 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4326. Min Act: -0.0000

Data Index: 299919 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4185. Min Act: -0.0000

Data Index: 576992 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4264. Min Act: -0.0000

Data Index: 13556 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4196. Min Act: -0.0001

Data Index: 377667 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4169. Min Act: -0.0000

Data Index: 682612 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4158. Min Act: -0.0000

Data Index: 99154 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4138. Min Act: -0.0001

Data Index: 827415 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1313139 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4222. Min Act: -0.0000

Data Index: 90797 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4023. Min Act: -0.0000

Data Index: 524683 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4007. Min Act: -0.0001

Data Index: 395483 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4143. Min Act: -0.0000

Data Index: 792992 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3897. Min Act: -0.0000

Data Index: 823704 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3744. Min Act: -0.0000

Data Index: 312247 (C4 (Web Text))

Max Activating Token Index: 448