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

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

Neuron 3376 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.5486. Min Act: -0.0000

Data Index: 861546 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.8811. Min Act: -0.0000

Data Index: 140212 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.7214. Min Act: -0.0001

Data Index: 338708 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.7408. Min Act: -0.0001

Data Index: 1310557 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.6420. Min Act: -0.0001

Data Index: 819411 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.4033. Min Act: -0.0000

Data Index: 89541 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.3826. Min Act: -0.0001

Data Index: 856930 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.3790. Min Act: -0.0001

Data Index: 707361 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.3712. Min Act: -0.0000

Data Index: 1312799 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.1379. Min Act: -0.0001

Data Index: 538587 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.1711. Min Act: -0.0001

Data Index: 466263 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.3837. Min Act: -0.0001

Data Index: 1163816 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.1397. Min Act: -0.0001

Data Index: 685604 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 3.5486. Min Range: -3.5486

Max Act: 2.1208. Min Act: -0.0001

Data Index: 212831 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 3.5486. Min Range: -3.5486

Max Act: 1.9584. Min Act: -0.0001

Data Index: 262372 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 3.5486. Min Range: -3.5486

Max Act: 1.9840. Min Act: -0.0001

Data Index: 53533 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 3.5486. Min Range: -3.5486

Max Act: 1.8500. Min Act: -0.0001

Data Index: 841948 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 3.5486. Min Range: -3.5486

Max Act: 1.8633. Min Act: -0.0001

Data Index: 1349757 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 3.5486. Min Range: -3.5486

Max Act: 1.9925. Min Act: -0.0000

Data Index: 1169200 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 3.5486. Min Range: -3.5486

Max Act: 1.9289. Min Act: -0.0001

Data Index: 986568 (C4 (Web Text))

Max Activating Token Index: 162