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

Dataset: The Pile

Neuron 3908 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: 1.2431. Min Range: -1.2431

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1021623 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1850303 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.1458. Min Act: -0.0000

Data Index: 314046 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.0052. Min Act: -0.0000

Data Index: 343806 (The Pile)

Max Activating Token Index: 585

Text #4

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1308245 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.0625. Min Act: -0.0000

Data Index: 478544 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1207763 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.1053. Min Act: -0.0000

Data Index: 1311705 (The Pile)

Max Activating Token Index: 966

Text #8

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.0078. Min Act: -0.0000

Data Index: 433617 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1519529 (The Pile)

Max Activating Token Index: 797

Text #10

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1784912 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8835. Min Act: -0.0000

Data Index: 206481 (The Pile)

Max Activating Token Index: 970

Text #12

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9015. Min Act: -0.0000

Data Index: 625999 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1684587 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1117280 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1939212 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1115197 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1218448 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8679. Min Act: -0.0000

Data Index: 215017 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8308. Min Act: -0.0000

Data Index: 838557 (The Pile)

Max Activating Token Index: 978