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

Dataset: The Pile

Neuron 4206 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1156338 (The Pile)

Max Activating Token Index: 721

Text #1

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1198576 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7128. Min Act: -0.0000

Data Index: 913422 (The Pile)

Max Activating Token Index: 724

Text #3

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6796. Min Act: -0.0000

Data Index: 146036 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6889. Min Act: -0.0000

Data Index: 763865 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6677. Min Act: -0.0000

Data Index: 196911 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1375598 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1050679 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6301. Min Act: -0.0000

Data Index: 516312 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6095. Min Act: -0.0000

Data Index: 909959 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1058462 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1165769 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6272. Min Act: -0.0000

Data Index: 304871 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1899167 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1578075 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1385333 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1674911 (The Pile)

Max Activating Token Index: 348

Text #17

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5532. Min Act: -0.0000

Data Index: 260105 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1884432 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5711. Min Act: -0.0000

Data Index: 931074 (The Pile)

Max Activating Token Index: 947