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

Dataset: The Pile

Neuron 4612 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: 0.7337. Min Range: -0.7337

Max Act: 0.7337. Min Act: -0.0000

Data Index: 946913 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1377916 (The Pile)

Max Activating Token Index: 181

Text #2

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6207. Min Act: -0.0000

Data Index: 409738 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1136643 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5929. Min Act: -0.0000

Data Index: 933036 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6287. Min Act: -0.0000

Data Index: 375287 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1832922 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1850095 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5991. Min Act: -0.0000

Data Index: 169435 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5803. Min Act: -0.0000

Data Index: 81405 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1123045 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1121304 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5672. Min Act: -0.0000

Data Index: 306234 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6028. Min Act: -0.0000

Data Index: 876567 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6015. Min Act: -0.0000

Data Index: 810027 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1575952 (The Pile)

Max Activating Token Index: 142

Text #16

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5766. Min Act: -0.0000

Data Index: 258416 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5911. Min Act: -0.0000

Data Index: 639776 (The Pile)

Max Activating Token Index: 137

Text #18

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5717. Min Act: -0.0000

Data Index: 679242 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6045. Min Act: -0.0000

Data Index: 58782 (The Pile)

Max Activating Token Index: 545