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

Dataset: The Pile

Neuron 293 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1062. Min Range: -1.1062

Max Act: 1.1062. Min Act: -0.0000

Data Index: 1259766 (The Pile)

Max Activating Token Index: 640

Text #1

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.9128. Min Act: -0.0000

Data Index: 71345 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.9188. Min Act: -0.0000

Data Index: 331679 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1134285 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1807739 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1835342 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.8632. Min Act: -0.0000

Data Index: 11854 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1510765 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1570733 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.8337. Min Act: -0.0000

Data Index: 580827 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.8523. Min Act: -0.0000

Data Index: 108270 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.7704. Min Act: -0.0000

Data Index: 922568 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.7920. Min Act: -0.0000

Data Index: 250320 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.7849. Min Act: -0.0000

Data Index: 1461430 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1573713 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1602253 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.7795. Min Act: -0.0000

Data Index: 167764 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.8054. Min Act: -0.0000

Data Index: 701124 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.7642. Min Act: -0.0000

Data Index: 412074 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 1.1062. Min Range: -1.1062

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1816677 (The Pile)

Max Activating Token Index: 418