Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3042 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6059. Min Act: -0.0000

Data Index: 1194994 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6211. Min Act: -0.0000

Data Index: 352522 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6840. Min Act: -0.0000

Data Index: 797275 (The Pile)

Max Activating Token Index: 840

Text #3

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4958. Min Act: -0.0000

Data Index: 822918 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4424. Min Act: -0.0000

Data Index: 19845 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5338. Min Act: -0.0000

Data Index: 399105 (The Pile)

Max Activating Token Index: 75

Text #6

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5475. Min Act: -0.0000

Data Index: 1544132 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5306. Min Act: -0.0000

Data Index: 1073332 (The Pile)

Max Activating Token Index: 402

Text #8

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5264. Min Act: -0.0000

Data Index: 518420 (The Pile)

Max Activating Token Index: 118

Text #9

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5067. Min Act: -0.0000

Data Index: 808586 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.3296. Min Act: -0.0000

Data Index: 1937263 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5422. Min Act: -0.0000

Data Index: 510683 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5891. Min Act: -0.0000

Data Index: 834908 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5001. Min Act: -0.0000

Data Index: 1058069 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4758. Min Act: -0.0000

Data Index: 1711268 (The Pile)

Max Activating Token Index: 376

Text #15

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1361450 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1919474 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4531. Min Act: -0.0000

Data Index: 1414677 (The Pile)

Max Activating Token Index: 872

Text #18

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4545. Min Act: -0.0000

Data Index: 106129 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4396. Min Act: -0.0000

Data Index: 26942 (The Pile)

Max Activating Token Index: 404