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

Dataset: The Pile

Neuron 669 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: 1.9557. Min Range: -1.9557

Max Act: 1.9557. Min Act: -0.0000

Data Index: 636539 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.5158. Min Act: -0.0000

Data Index: 1896428 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.5133. Min Act: -0.0000

Data Index: 761735 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.3847. Min Act: -0.0000

Data Index: 1034921 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.3782. Min Act: -0.0000

Data Index: 437265 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.4340. Min Act: -0.0000

Data Index: 1088021 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.4347. Min Act: -0.0000

Data Index: 449087 (The Pile)

Max Activating Token Index: 61

Text #7

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.4043. Min Act: -0.0000

Data Index: 574054 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.4513. Min Act: -0.0000

Data Index: 846191 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.4094. Min Act: -0.0000

Data Index: 703847 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1161159 (The Pile)

Max Activating Token Index: 855

Text #11

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.2236. Min Act: -0.0000

Data Index: 175803 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.2126. Min Act: -0.0000

Data Index: 222289 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1291701 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.2087. Min Act: -0.0000

Data Index: 1002866 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.2757. Min Act: -0.0000

Data Index: 1707964 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.1991. Min Act: -0.0000

Data Index: 57664 (The Pile)

Max Activating Token Index: 711

Text #17

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.3373. Min Act: -0.0000

Data Index: 420873 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1820490 (The Pile)

Max Activating Token Index: 318

Text #19

Max Range: 1.9557. Min Range: -1.9557

Max Act: 1.3689. Min Act: -0.0000

Data Index: 1856278 (The Pile)

Max Activating Token Index: 836