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

Dataset: The Pile

Neuron 1089 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1235271 (The Pile)

Max Activating Token Index: 74

Text #1

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.8832. Min Act: -0.0000

Data Index: 281001 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7515. Min Act: -0.0000

Data Index: 718050 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7015. Min Act: -0.0000

Data Index: 334674 (The Pile)

Max Activating Token Index: 299

Text #4

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.6661. Min Act: -0.0000

Data Index: 312389 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.6530. Min Act: -0.0000

Data Index: 467025 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1896205 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1829671 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.5641. Min Act: -0.0000

Data Index: 113315 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.5650. Min Act: -0.0000

Data Index: 995393 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.5729. Min Act: -0.0000

Data Index: 703511 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.6033. Min Act: -0.0000

Data Index: 315929 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.5648. Min Act: -0.0000

Data Index: 935449 (The Pile)

Max Activating Token Index: 225

Text #13

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1626847 (The Pile)

Max Activating Token Index: 494

Text #14

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.5268. Min Act: -0.0000

Data Index: 380629 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1258808 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1114799 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.5145. Min Act: -0.0000

Data Index: 624975 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.5385. Min Act: -0.0000

Data Index: 668830 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1592518 (The Pile)

Max Activating Token Index: 666