Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 576 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.6124. Min Act: -0.0001

Data Index: 669391 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.4284. Min Act: -0.0001

Data Index: 716773 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.4160. Min Act: -0.0001

Data Index: 1243279 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.4112. Min Act: -0.0001

Data Index: 920867 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.3585. Min Act: -0.0001

Data Index: 80118 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.1986. Min Act: -0.0001

Data Index: 103577 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.4166. Min Act: -0.0001

Data Index: 1306626 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.1385. Min Act: -0.0001

Data Index: 779606 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2395. Min Act: -0.0001

Data Index: 502889 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.1656. Min Act: -0.0001

Data Index: 1257262 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.1547. Min Act: -0.0001

Data Index: 513269 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.1313. Min Act: -0.0001

Data Index: 1259803 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2011. Min Act: -0.0001

Data Index: 940393 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.0801. Min Act: -0.0001

Data Index: 108223 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.1152. Min Act: -0.0001

Data Index: 341153 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.1095. Min Act: -0.0001

Data Index: 477371 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.1240. Min Act: -0.0001

Data Index: 533095 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 1.6124. Min Range: -1.6124

Max Act: 0.9834. Min Act: -0.0001

Data Index: 423098 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.0722. Min Act: -0.0001

Data Index: 1171661 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 1.6124. Min Range: -1.6124

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1116709 (C4 (Web Text))

Max Activating Token Index: 783