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

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

Neuron 1648 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.2926. Min Act: -0.0000

Data Index: 550979 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.4212. Min Act: -0.0000

Data Index: 991971 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.0975. Min Act: -0.0000

Data Index: 29511 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.0203. Min Act: -0.0000

Data Index: 673298 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.1421. Min Act: -0.0000

Data Index: 584512 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.1288. Min Act: -0.0000

Data Index: 1114974 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.1192. Min Act: -0.0000

Data Index: 352298 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.1303. Min Act: -0.0000

Data Index: 493584 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 3.4212. Min Range: -3.4212

Max Act: 2.9661. Min Act: -0.0000

Data Index: 1328796 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 3.4212. Min Range: -3.4212

Max Act: 2.9392. Min Act: -0.0000

Data Index: 1546980 (Python Code)

Max Activating Token Index: 601

Text #10

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.0742. Min Act: -0.0000

Data Index: 125267 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.0697. Min Act: -0.0000

Data Index: 1483589 (Python Code)

Max Activating Token Index: 457

Text #12

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.0702. Min Act: -0.0000

Data Index: 629063 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.0352. Min Act: -0.0000

Data Index: 1483423 (Python Code)

Max Activating Token Index: 798

Text #14

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.1818. Min Act: -0.0000

Data Index: 552533 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.0384. Min Act: -0.0000

Data Index: 1531457 (Python Code)

Max Activating Token Index: 683

Text #16

Max Range: 3.4212. Min Range: -3.4212

Max Act: 2.8811. Min Act: -0.0000

Data Index: 1395317 (Python Code)

Max Activating Token Index: 335

Text #17

Max Range: 3.4212. Min Range: -3.4212

Max Act: 2.8569. Min Act: -0.0000

Data Index: 342659 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 3.4212. Min Range: -3.4212

Max Act: 2.8571. Min Act: -0.0000

Data Index: 1212818 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 3.4212. Min Range: -3.4212

Max Act: 3.1289. Min Act: -0.0000

Data Index: 257921 (C4 (Web Text))

Max Activating Token Index: 336