Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3877 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.4368. Min Act: -0.0001

Data Index: 588556 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.4153. Min Act: -0.0001

Data Index: 476433 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.3143. Min Act: -0.0001

Data Index: 769463 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.2545. Min Act: -0.0001

Data Index: 570165 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.2355. Min Act: -0.0001

Data Index: 958838 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.1587. Min Act: -0.0001

Data Index: 771462 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.2361. Min Act: -0.0001

Data Index: 511963 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.1917. Min Act: -0.0001

Data Index: 149167 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.2048. Min Act: -0.0001

Data Index: 1088595 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.1878. Min Act: -0.0001

Data Index: 1072683 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0310. Min Act: -0.0001

Data Index: 1260109 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0635. Min Act: -0.0001

Data Index: 510870 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0778. Min Act: -0.0001

Data Index: 1301389 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0176. Min Act: -0.0001

Data Index: 584198 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0033. Min Act: -0.0001

Data Index: 861578 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9283. Min Act: -0.0001

Data Index: 1341331 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9005. Min Act: -0.0001

Data Index: 1318085 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9304. Min Act: -0.0001

Data Index: 1961 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9900. Min Act: -0.0001

Data Index: 245613 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9022. Min Act: -0.0001

Data Index: 663502 (C4 (Web Text))

Max Activating Token Index: 1001