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

Dataset: The Pile

Neuron 2333 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.4101. Min Act: -0.0000

Data Index: 765800 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 3.4101. Min Range: -3.4101

Max Act: 2.4788. Min Act: -0.0000

Data Index: 1632722 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 3.4101. Min Range: -3.4101

Max Act: 2.2994. Min Act: -0.0000

Data Index: 1469193 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 3.4101. Min Range: -3.4101

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1971163 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 3.4101. Min Range: -3.4101

Max Act: 2.1623. Min Act: -0.0000

Data Index: 860595 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 3.4101. Min Range: -3.4101

Max Act: 2.0701. Min Act: -0.0000

Data Index: 1364939 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.9280. Min Act: -0.0000

Data Index: 1990762 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.9036. Min Act: -0.0000

Data Index: 150973 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.8995. Min Act: -0.0000

Data Index: 34850 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.7092. Min Act: -0.0000

Data Index: 428666 (The Pile)

Max Activating Token Index: 755

Text #10

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.6151. Min Act: -0.0000

Data Index: 1027194 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.5049. Min Act: -0.0000

Data Index: 1973464 (The Pile)

Max Activating Token Index: 375

Text #12

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.5041. Min Act: -0.0000

Data Index: 810770 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.4561. Min Act: -0.0000

Data Index: 851538 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.5893. Min Act: -0.0000

Data Index: 1080517 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.5859. Min Act: -0.0000

Data Index: 490540 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.5638. Min Act: -0.0000

Data Index: 3853 (The Pile)

Max Activating Token Index: 44

Text #17

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.5270. Min Act: -0.0000

Data Index: 151670 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.5084. Min Act: -0.0000

Data Index: 774807 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 3.4101. Min Range: -3.4101

Max Act: 1.3288. Min Act: -0.0000

Data Index: 796994 (The Pile)

Max Activating Token Index: 1010