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

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

Neuron 5930 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: 0.7347. Min Range: -0.7347

Max Act: 0.7347. Min Act: 0.0000

Data Index: 1305521 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6903. Min Act: -0.0000

Data Index: 731053 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6325. Min Act: -0.0000

Data Index: 187384 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6730. Min Act: -0.0000

Data Index: 340104 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6588. Min Act: -0.0000

Data Index: 440186 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6182. Min Act: 0.0000

Data Index: 672485 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1124935 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5630. Min Act: -0.0000

Data Index: 149338 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6145. Min Act: -0.0000

Data Index: 265340 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5818. Min Act: -0.0000

Data Index: 354437 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5791. Min Act: -0.0000

Data Index: 37752 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1032823 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5916. Min Act: -0.0000

Data Index: 39599 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5668. Min Act: -0.0000

Data Index: 120517 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5381. Min Act: -0.0000

Data Index: 955294 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1312902 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5456. Min Act: 0.0000

Data Index: 728330 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1304871 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5315. Min Act: -0.0000

Data Index: 74068 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5184. Min Act: -0.0000

Data Index: 45486 (C4 (Web Text))

Max Activating Token Index: 545