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

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

Neuron 563 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: 1.9120. Min Range: -1.9120

Max Act: 1.9120. Min Act: -0.0000

Data Index: 367731 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.7807. Min Act: -0.0001

Data Index: 463820 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.7796. Min Act: -0.0000

Data Index: 610155 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.7694. Min Act: -0.0000

Data Index: 1246036 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.6268. Min Act: -0.0000

Data Index: 191268 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.6156. Min Act: -0.0000

Data Index: 170628 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.3989. Min Act: -0.0000

Data Index: 83615 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.4435. Min Act: -0.0000

Data Index: 970217 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.3272. Min Act: -0.0000

Data Index: 1011976 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.3857. Min Act: -0.0000

Data Index: 553552 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.3765. Min Act: -0.0001

Data Index: 929951 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.3386. Min Act: -0.0000

Data Index: 276239 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.4228. Min Act: -0.0000

Data Index: 708158 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.3644. Min Act: -0.0000

Data Index: 282744 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.3106. Min Act: -0.0001

Data Index: 747104 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.2212. Min Act: -0.0000

Data Index: 437094 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.2471. Min Act: -0.0000

Data Index: 299231 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.2923. Min Act: -0.0000

Data Index: 711173 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.2056. Min Act: -0.0000

Data Index: 439176 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.9120. Min Range: -1.9120

Max Act: 1.3131. Min Act: -0.0000

Data Index: 856260 (C4 (Web Text))

Max Activating Token Index: 366