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

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

Neuron 4207 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1846. Min Act: -0.0000

Data Index: 898622 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.2875. Min Act: -0.0000

Data Index: 21698 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0884. Min Act: -0.0000

Data Index: 1012010 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.2110. Min Act: -0.0000

Data Index: 1234342 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1442. Min Act: -0.0000

Data Index: 517246 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1576. Min Act: -0.0000

Data Index: 672314 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1387. Min Act: -0.0000

Data Index: 28297 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.2416. Min Act: -0.0000

Data Index: 993342 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0572. Min Act: -0.0000

Data Index: 40798 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1835. Min Act: -0.0000

Data Index: 1241442 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 3.2875. Min Range: -3.2875

Max Act: 2.8874. Min Act: -0.0000

Data Index: 429770 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 3.2875. Min Range: -3.2875

Max Act: 2.8761. Min Act: -0.0000

Data Index: 181859 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 3.2875. Min Range: -3.2875

Max Act: 2.8881. Min Act: -0.0000

Data Index: 556334 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0075. Min Act: -0.0000

Data Index: 1045170 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 3.2875. Min Range: -3.2875

Max Act: 2.9468. Min Act: -0.0000

Data Index: 559615 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 3.2875. Min Range: -3.2875

Max Act: 2.9392. Min Act: -0.0000

Data Index: 1146252 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 3.2875. Min Range: -3.2875

Max Act: 2.9667. Min Act: -0.0000

Data Index: 1481515 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 3.2875. Min Range: -3.2875

Max Act: 2.8264. Min Act: -0.0000

Data Index: 1298633 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 3.2875. Min Range: -3.2875

Max Act: 2.7616. Min Act: -0.0000

Data Index: 928154 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 3.2875. Min Range: -3.2875

Max Act: 2.7720. Min Act: -0.0000

Data Index: 865189 (C4 (Web Text))

Max Activating Token Index: 359