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

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

Neuron 3249 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: 3.8495. Min Range: -3.8495

Max Act: 3.8495. Min Act: -0.0001

Data Index: 933579 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.8224. Min Act: -0.0001

Data Index: 804749 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.4155. Min Act: -0.0001

Data Index: 26216 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.8788. Min Act: -0.0001

Data Index: 637225 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.2750. Min Act: -0.0001

Data Index: 1067099 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.0860. Min Act: -0.0001

Data Index: 216959 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.1535. Min Act: -0.0001

Data Index: 606087 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.9523. Min Act: -0.0001

Data Index: 249478 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.8151. Min Act: -0.0001

Data Index: 615935 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.9030. Min Act: -0.0001

Data Index: 472462 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.9012. Min Act: -0.0001

Data Index: 1134457 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.7110. Min Act: -0.0001

Data Index: 1186518 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.1114. Min Act: -0.0001

Data Index: 442765 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.8260. Min Act: -0.0001

Data Index: 620225 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.6895. Min Act: -0.0001

Data Index: 1244597 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.5421. Min Act: -0.0001

Data Index: 319175 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.8018. Min Act: -0.0001

Data Index: 232444 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.5183. Min Act: -0.0001

Data Index: 189006 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.5214. Min Act: -0.0001

Data Index: 713038 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.6325. Min Act: -0.0001

Data Index: 465247 (C4 (Web Text))

Max Activating Token Index: 275