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

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

Neuron 5831 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: 1.4509. Min Range: -1.4509

Max Act: 1.4509. Min Act: -0.0000

Data Index: 134756 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1840. Min Act: -0.0000

Data Index: 709623 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1659. Min Act: -0.0000

Data Index: 728396 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1154. Min Act: -0.0000

Data Index: 490002 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1138. Min Act: -0.0000

Data Index: 345377 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1269675 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0250. Min Act: -0.0000

Data Index: 147224 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9461. Min Act: -0.0000

Data Index: 15745 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0053. Min Act: -0.0000

Data Index: 8010 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9445. Min Act: -0.0000

Data Index: 534990 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0560. Min Act: -0.0000

Data Index: 849114 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9984. Min Act: -0.0000

Data Index: 508000 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9280. Min Act: -0.0000

Data Index: 292055 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9724. Min Act: -0.0000

Data Index: 855469 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9693. Min Act: -0.0000

Data Index: 258152 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9254. Min Act: -0.0000

Data Index: 414387 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9327. Min Act: -0.0000

Data Index: 317330 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1018570 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.8973. Min Act: -0.0000

Data Index: 268563 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1059645 (C4 (Web Text))

Max Activating Token Index: 655