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

Dataset: The Pile

Neuron 1038 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1374596 (The Pile)

Max Activating Token Index: 662

Text #1

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3806. Min Act: -0.0000

Data Index: 641903 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1766839 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1819912 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1549005 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1553993 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1045699 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1490977 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3489. Min Act: -0.0000

Data Index: 941953 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1351812 (The Pile)

Max Activating Token Index: 65

Text #10

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3342. Min Act: -0.0000

Data Index: 803061 (The Pile)

Max Activating Token Index: 141

Text #11

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1996538 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3232. Min Act: -0.0000

Data Index: 812597 (The Pile)

Max Activating Token Index: 792

Text #13

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3256. Min Act: -0.0000

Data Index: 647161 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1295602 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1390764 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1705975 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3273. Min Act: -0.0000

Data Index: 754989 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3217. Min Act: 0.0000

Data Index: 1905058 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1478306 (The Pile)

Max Activating Token Index: 20