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

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

Neuron 3831 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1152. Min Range: -1.1152

Max Act: 1.1152. Min Act: -0.0000

Data Index: 585324 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.1152. Min Range: -1.1152

Max Act: 1.0337. Min Act: -0.0000

Data Index: 161710 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.9122. Min Act: -0.0000

Data Index: 330777 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.9420. Min Act: 0.0000

Data Index: 1123806 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.9282. Min Act: 0.0001

Data Index: 398359 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1034652 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.8883. Min Act: -0.0000

Data Index: 794398 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.9255. Min Act: -0.0000

Data Index: 503661 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.8612. Min Act: -0.0000

Data Index: 39884 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.8104. Min Act: 0.0001

Data Index: 996199 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1015493 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.7904. Min Act: 0.0000

Data Index: 883011 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.8182. Min Act: 0.0000

Data Index: 1227389 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.7973. Min Act: 0.0000

Data Index: 811265 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.7942. Min Act: 0.0000

Data Index: 1159070 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.8087. Min Act: -0.0000

Data Index: 228239 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.7354. Min Act: -0.0000

Data Index: 622587 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.7759. Min Act: 0.0000

Data Index: 1233171 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.7653. Min Act: -0.0000

Data Index: 151147 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.7656. Min Act: 0.0000

Data Index: 1181490 (C4 (Web Text))

Max Activating Token Index: 618