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

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

Neuron 5695 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.6854. Min Act: -0.0000

Data Index: 1206897 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.5333. Min Act: -0.0000

Data Index: 651259 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.5899. Min Act: -0.0000

Data Index: 23703 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.5386. Min Act: -0.0000

Data Index: 515582 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.4815. Min Act: -0.0000

Data Index: 541992 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.4614. Min Act: -0.0000

Data Index: 784361 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.4349. Min Act: -0.0000

Data Index: 812991 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.4057. Min Act: -0.0000

Data Index: 1099996 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.2969. Min Act: -0.0000

Data Index: 299302 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.3746. Min Act: -0.0000

Data Index: 1060126 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.4730. Min Act: -0.0000

Data Index: 378401 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.2731. Min Act: -0.0000

Data Index: 305060 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.2478. Min Act: -0.0000

Data Index: 768870 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.1203. Min Act: -0.0000

Data Index: 610291 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.1992. Min Act: -0.0000

Data Index: 322678 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.1912. Min Act: -0.0000

Data Index: 1070761 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.1506. Min Act: -0.0000

Data Index: 618863 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.1449. Min Act: -0.0000

Data Index: 1046380 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.1343. Min Act: -0.0000

Data Index: 507494 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 2.6854. Min Range: -2.6854

Max Act: 2.2549. Min Act: -0.0000

Data Index: 729554 (C4 (Web Text))

Max Activating Token Index: 979