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

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

Neuron 3520 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.4437. Min Act: -0.0000

Data Index: 995062 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.4135. Min Act: -0.0000

Data Index: 957690 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.1952. Min Act: -0.0000

Data Index: 992939 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.1942. Min Act: -0.0000

Data Index: 267535 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.2852. Min Act: -0.0000

Data Index: 281793 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.1065. Min Act: -0.0000

Data Index: 150198 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0587. Min Act: -0.0000

Data Index: 1358178 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.9882. Min Act: -0.0000

Data Index: 191337 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.9960. Min Act: -0.0000

Data Index: 114434 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1054822 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.9187. Min Act: -0.0000

Data Index: 789070 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1150663 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0095. Min Act: -0.0000

Data Index: 928692 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0099. Min Act: -0.0000

Data Index: 977340 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.9994. Min Act: -0.0000

Data Index: 379653 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0051. Min Act: 0.0000

Data Index: 1156358 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0016. Min Act: -0.0000

Data Index: 464627 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.9937. Min Act: -0.0000

Data Index: 1128572 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.9820. Min Act: 0.0000

Data Index: 183726 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.9101. Min Act: -0.0000

Data Index: 707301 (C4 (Web Text))

Max Activating Token Index: 1018