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

Dataset: The Pile

Neuron 1555 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: 0.8185. Min Range: -0.8185

Max Act: 0.8167. Min Act: -0.0000

Data Index: 325371 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1688983 (The Pile)

Max Activating Token Index: 612

Text #2

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1730421 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1576118 (The Pile)

Max Activating Token Index: 537

Text #4

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.7539. Min Act: -0.0000

Data Index: 727014 (The Pile)

Max Activating Token Index: 240

Text #5

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.7343. Min Act: -0.0000

Data Index: 495155 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1629754 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1799630 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1196399 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1967696 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.6660. Min Act: -0.0000

Data Index: 434274 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1599900 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.6650. Min Act: -0.0000

Data Index: 137457 (The Pile)

Max Activating Token Index: 99

Text #13

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1100618 (The Pile)

Max Activating Token Index: 654

Text #14

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.6985. Min Act: -0.0000

Data Index: 732948 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1579899 (The Pile)

Max Activating Token Index: 104

Text #16

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.7042. Min Act: -0.0000

Data Index: 195357 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.6599. Min Act: -0.0000

Data Index: 56974 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1811952 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 0.8185. Min Range: -0.8185

Max Act: 0.6534. Min Act: -0.0000

Data Index: 91816 (The Pile)

Max Activating Token Index: 472