Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1440 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.7206. Min Range: -5.7206

Max Act: 5.7206. Min Act: -0.0001

Data Index: 1187715 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.9457. Min Act: -0.0001

Data Index: 255630 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.9900. Min Act: -0.0001

Data Index: 733173 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.9507. Min Act: -0.0001

Data Index: 355520 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.9554. Min Act: -0.0001

Data Index: 1339160 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.8911. Min Act: -0.0001

Data Index: 45160 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.7912. Min Act: -0.0001

Data Index: 1041271 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.7605. Min Act: -0.0001

Data Index: 677890 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.7681. Min Act: -0.0001

Data Index: 146071 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.9194. Min Act: -0.0001

Data Index: 22911 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.5383. Min Act: -0.0001

Data Index: 828493 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.5471. Min Act: -0.0001

Data Index: 450635 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.5386. Min Act: -0.0001

Data Index: 847970 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.8879. Min Act: -0.0001

Data Index: 260968 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.4202. Min Act: -0.0001

Data Index: 64715 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.6025. Min Act: -0.0001

Data Index: 742963 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.3898. Min Act: -0.0001

Data Index: 496136 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.3996. Min Act: -0.0001

Data Index: 520263 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.5764. Min Act: -0.0001

Data Index: 831212 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 5.7206. Min Range: -5.7206

Max Act: 4.5685. Min Act: -0.0001

Data Index: 156286 (C4 (Web Text))

Max Activating Token Index: 710