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

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

Neuron 3163 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.6515. Min Act: -0.0000

Data Index: 560550 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 3.6515. Min Range: -3.6515

Max Act: 2.2778. Min Act: -0.0000

Data Index: 1240289 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 3.6515. Min Range: -3.6515

Max Act: 2.2232. Min Act: -0.0000

Data Index: 1326367 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 3.6515. Min Range: -3.6515

Max Act: 2.0786. Min Act: -0.0000

Data Index: 254623 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 3.6515. Min Range: -3.6515

Max Act: 2.0042. Min Act: -0.0000

Data Index: 689862 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.9618. Min Act: -0.0000

Data Index: 97730 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.8545. Min Act: -0.0000

Data Index: 240467 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.7473. Min Act: -0.0000

Data Index: 224785 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.8377. Min Act: -0.0000

Data Index: 1032001 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.8331. Min Act: -0.0000

Data Index: 542150 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.7898. Min Act: -0.0000

Data Index: 1169617 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.7722. Min Act: -0.0000

Data Index: 7596 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.6805. Min Act: -0.0000

Data Index: 725648 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.8749. Min Act: -0.0000

Data Index: 167637 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.8669. Min Act: -0.0000

Data Index: 619632 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.6801. Min Act: -0.0000

Data Index: 529120 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.7630. Min Act: -0.0000

Data Index: 231980 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.7327. Min Act: -0.0000

Data Index: 969789 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.7262. Min Act: -0.0000

Data Index: 754987 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 3.6515. Min Range: -3.6515

Max Act: 1.6469. Min Act: -0.0000

Data Index: 197811 (C4 (Web Text))

Max Activating Token Index: 258