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

Dataset: The Pile

Neuron 621 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: 1.3143. Min Range: -1.3143

Max Act: 1.3143. Min Act: -0.0000

Data Index: 1506573 (The Pile)

Max Activating Token Index: 309

Text #1

Max Range: 1.3143. Min Range: -1.3143

Max Act: 1.2335. Min Act: -0.0000

Data Index: 1338786 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1400120 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.9357. Min Act: -0.0000

Data Index: 133780 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8843. Min Act: 0.0000

Data Index: 1802096 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.9352. Min Act: -0.0000

Data Index: 321187 (The Pile)

Max Activating Token Index: 769

Text #6

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8698. Min Act: -0.0000

Data Index: 849560 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1596399 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8438. Min Act: 0.0001

Data Index: 1770071 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8478. Min Act: -0.0000

Data Index: 622021 (The Pile)

Max Activating Token Index: 183

Text #10

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8251. Min Act: 0.0002

Data Index: 1485831 (The Pile)

Max Activating Token Index: 287

Text #11

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1168013 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8138. Min Act: -0.0000

Data Index: 690977 (The Pile)

Max Activating Token Index: 840

Text #13

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1131128 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1725149 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7832. Min Act: -0.0000

Data Index: 913590 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7809. Min Act: 0.0000

Data Index: 1743204 (The Pile)

Max Activating Token Index: 438

Text #17

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1546641 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1846513 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7525. Min Act: 0.0000

Data Index: 1138670 (The Pile)

Max Activating Token Index: 230