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

Dataset: The Pile

Neuron 4120 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.3198. Min Act: -0.0000

Data Index: 83134 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.2100. Min Act: -0.0000

Data Index: 1733918 (The Pile)

Max Activating Token Index: 600

Text #2

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.1111. Min Act: -0.0000

Data Index: 426586 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1547986 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1684958 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.0241. Min Act: -0.0000

Data Index: 189374 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1481625 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1840405 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9035. Min Act: -0.0000

Data Index: 839438 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9230. Min Act: -0.0000

Data Index: 916949 (The Pile)

Max Activating Token Index: 46

Text #10

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1379178 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8385. Min Act: -0.0000

Data Index: 790261 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.7740. Min Act: -0.0000

Data Index: 22589 (The Pile)

Max Activating Token Index: 410

Text #13

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1194347 (The Pile)

Max Activating Token Index: 246

Text #14

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1650992 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1882469 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1170067 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1331121 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1446398 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1331250 (The Pile)

Max Activating Token Index: 384