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

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

Neuron 1948 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8845. Min Range: -3.8845

Max Act: 3.8845. Min Act: -0.0000

Data Index: 1008120 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 3.8845. Min Range: -3.8845

Max Act: 3.6553. Min Act: -0.0000

Data Index: 192183 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 3.8845. Min Range: -3.8845

Max Act: 3.1908. Min Act: -0.0000

Data Index: 103926 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 3.8845. Min Range: -3.8845

Max Act: 3.3002. Min Act: -0.0000

Data Index: 614277 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 3.8845. Min Range: -3.8845

Max Act: 3.1459. Min Act: -0.0000

Data Index: 1153654 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.5655. Min Act: -0.0000

Data Index: 493383 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.6204. Min Act: -0.0000

Data Index: 418071 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.4465. Min Act: -0.0000

Data Index: 859095 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.2038. Min Act: -0.0000

Data Index: 1176801 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.3352. Min Act: -0.0000

Data Index: 737877 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.2828. Min Act: -0.0000

Data Index: 1261476 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.2969. Min Act: -0.0000

Data Index: 1026023 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.3475. Min Act: -0.0000

Data Index: 1157805 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.1878. Min Act: -0.0000

Data Index: 724597 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.1819. Min Act: -0.0000

Data Index: 1451005 (Python Code)

Max Activating Token Index: 751

Text #15

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.1700. Min Act: -0.0000

Data Index: 203930 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.0588. Min Act: -0.0000

Data Index: 616540 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.1181. Min Act: -0.0000

Data Index: 1214430 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.1210. Min Act: -0.0000

Data Index: 1379936 (Python Code)

Max Activating Token Index: 256

Text #19

Max Range: 3.8845. Min Range: -3.8845

Max Act: 2.0998. Min Act: -0.0000

Data Index: 1469936 (Python Code)

Max Activating Token Index: 463