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

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

Neuron 4518 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2898. Min Range: -2.2898

Max Act: 2.2898. Min Act: -0.0000

Data Index: 613555 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 2.2898. Min Range: -2.2898

Max Act: 2.1244. Min Act: -0.0000

Data Index: 133652 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 2.2898. Min Range: -2.2898

Max Act: 2.0601. Min Act: -0.0000

Data Index: 1001036 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 2.2898. Min Range: -2.2898

Max Act: 2.1239. Min Act: -0.0000

Data Index: 111129 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 2.2898. Min Range: -2.2898

Max Act: 2.1248. Min Act: -0.0000

Data Index: 1230675 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.9973. Min Act: -0.0000

Data Index: 47015 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.9062. Min Act: -0.0000

Data Index: 1128128 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.9512. Min Act: -0.0000

Data Index: 1148174 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.9514. Min Act: -0.0000

Data Index: 185896 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.7500. Min Act: -0.0000

Data Index: 1053970 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8102. Min Act: -0.0000

Data Index: 1027675 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.7570. Min Act: -0.0000

Data Index: 1156642 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8540. Min Act: -0.0000

Data Index: 1251787 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8475. Min Act: -0.0000

Data Index: 507741 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.9452. Min Act: -0.0000

Data Index: 353181 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8408. Min Act: -0.0000

Data Index: 1172861 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8093. Min Act: -0.0000

Data Index: 414590 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.7700. Min Act: -0.0000

Data Index: 453297 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.6217. Min Act: -0.0000

Data Index: 484188 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.7020. Min Act: -0.0000

Data Index: 1013334 (C4 (Web Text))

Max Activating Token Index: 64