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

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

Neuron 4459 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: 0.4368. Min Range: -0.4368

Max Act: 0.4368. Min Act: -0.0000

Data Index: 32290 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.4078. Min Act: 0.0000

Data Index: 552472 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.4000. Min Act: -0.0000

Data Index: 753743 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3884. Min Act: -0.0000

Data Index: 849584 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1137572 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.4025. Min Act: 0.0000

Data Index: 1288997 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3630. Min Act: 0.0000

Data Index: 1065739 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3631. Min Act: 0.0001

Data Index: 1235329 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1205031 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3505. Min Act: -0.0000

Data Index: 889486 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3594. Min Act: -0.0000

Data Index: 15703 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3722. Min Act: -0.0000

Data Index: 687379 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1253944 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1254329 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1274170 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3365. Min Act: -0.0000

Data Index: 966791 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3443. Min Act: 0.0001

Data Index: 655538 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3423. Min Act: 0.0000

Data Index: 701689 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1325642 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.4368. Min Range: -0.4368

Max Act: 0.3370. Min Act: 0.0000

Data Index: 967923 (C4 (Web Text))

Max Activating Token Index: 30