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

Dataset: The Pile

Neuron 2460 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.9793. Min Act: -0.0000

Data Index: 389739 (The Pile)

Max Activating Token Index: 367

Text #1

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1223259 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.7894. Min Act: -0.0000

Data Index: 294471 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1001559 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8698. Min Act: -0.0000

Data Index: 201438 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8834. Min Act: -0.0000

Data Index: 262824 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8041. Min Act: -0.0000

Data Index: 837583 (The Pile)

Max Activating Token Index: 597

Text #7

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8538. Min Act: -0.0000

Data Index: 424157 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8215. Min Act: -0.0000

Data Index: 688700 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.7909. Min Act: -0.0000

Data Index: 969283 (The Pile)

Max Activating Token Index: 441

Text #10

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1034953 (The Pile)

Max Activating Token Index: 908

Text #11

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1588792 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1168327 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1084427 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1884780 (The Pile)

Max Activating Token Index: 69

Text #15

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1044786 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1153709 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1141475 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1416094 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 0.9793. Min Range: -0.9793

Max Act: 0.7572. Min Act: -0.0000

Data Index: 161801 (The Pile)

Max Activating Token Index: 532