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

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

Neuron 3667 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.2074. Min Act: -0.0000

Data Index: 273060 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.1535. Min Act: -0.0000

Data Index: 498636 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.9832. Min Act: -0.0000

Data Index: 1175058 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.8895. Min Act: -0.0000

Data Index: 1276953 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.8499. Min Act: -0.0000

Data Index: 155031 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.9923. Min Act: -0.0000

Data Index: 842856 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.6382. Min Act: -0.0000

Data Index: 1029788 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.7034. Min Act: -0.0000

Data Index: 584025 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.6570. Min Act: -0.0000

Data Index: 260109 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.6205. Min Act: -0.0000

Data Index: 762703 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.4333. Min Act: -0.0000

Data Index: 62322 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.5978. Min Act: -0.0000

Data Index: 793363 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.4201. Min Act: -0.0000

Data Index: 1080905 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.5734. Min Act: -0.0000

Data Index: 160084 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.5500. Min Act: -0.0000

Data Index: 38522 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.5288. Min Act: -0.0000

Data Index: 987898 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.5166. Min Act: -0.0000

Data Index: 200215 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.4950. Min Act: -0.0000

Data Index: 207412 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.5023. Min Act: -0.0000

Data Index: 1092850 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 4.2074. Min Range: -4.2074

Max Act: 3.3361. Min Act: -0.0000

Data Index: 496437 (C4 (Web Text))

Max Activating Token Index: 986