Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2616 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6750. Min Range: -2.6750

Max Act: 2.6750. Min Act: -0.0000

Data Index: 562879 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 2.6750. Min Range: -2.6750

Max Act: 2.2150. Min Act: -0.0000

Data Index: 312872 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 2.6750. Min Range: -2.6750

Max Act: 2.1230. Min Act: -0.0000

Data Index: 863642 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.9897. Min Act: -0.0000

Data Index: 878936 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.8431. Min Act: -0.0001

Data Index: 1648447 (Python Code)

Max Activating Token Index: 750

Text #5

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.6280. Min Act: -0.0001

Data Index: 1554180 (Python Code)

Max Activating Token Index: 1018

Text #6

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.6854. Min Act: -0.0000

Data Index: 552532 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.6728. Min Act: -0.0000

Data Index: 1056608 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.5579. Min Act: -0.0000

Data Index: 1123420 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.7352. Min Act: -0.0000

Data Index: 1344230 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.6183. Min Act: -0.0000

Data Index: 538015 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.5863. Min Act: -0.0000

Data Index: 365525 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.5769. Min Act: -0.0000

Data Index: 111342 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.6554. Min Act: -0.0000

Data Index: 1098834 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.5574. Min Act: 0.0000

Data Index: 918948 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1005170 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.5462. Min Act: -0.0000

Data Index: 1273511 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.5836. Min Act: -0.0000

Data Index: 1655214 (Python Code)

Max Activating Token Index: 806

Text #18

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.5285. Min Act: -0.0000

Data Index: 705061 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 2.6750. Min Range: -2.6750

Max Act: 1.5067. Min Act: -0.0000

Data Index: 1247618 (C4 (Web Text))

Max Activating Token Index: 78