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

Dataset: The Pile

Neuron 3107 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1034390 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1576796 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.0350. Min Act: -0.0000

Data Index: 1663981 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1566881 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.0379. Min Act: -0.0000

Data Index: 460978 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.0242. Min Act: -0.0000

Data Index: 332954 (The Pile)

Max Activating Token Index: 307

Text #6

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1843349 (The Pile)

Max Activating Token Index: 57

Text #7

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9392. Min Act: -0.0000

Data Index: 212217 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1226466 (The Pile)

Max Activating Token Index: 908

Text #9

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9324. Min Act: -0.0000

Data Index: 667363 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1650577 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8478. Min Act: -0.0000

Data Index: 1495659 (The Pile)

Max Activating Token Index: 404

Text #12

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8387. Min Act: -0.0000

Data Index: 562591 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8845. Min Act: -0.0000

Data Index: 1823172 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1478950 (The Pile)

Max Activating Token Index: 625

Text #15

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.7992. Min Act: -0.0000

Data Index: 249755 (The Pile)

Max Activating Token Index: 853

Text #16

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.7989. Min Act: 0.0000

Data Index: 105088 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1771148 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1080853 (The Pile)

Max Activating Token Index: 166

Text #19

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.7923. Min Act: -0.0000

Data Index: 385685 (The Pile)

Max Activating Token Index: 625