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

Dataset: The Pile

Neuron 256 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.8094. Min Act: -0.0000

Data Index: 452451 (The Pile)

Max Activating Token Index: 347

Text #1

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.8019. Min Act: -0.0000

Data Index: 55481 (The Pile)

Max Activating Token Index: 203

Text #2

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1317343 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1695567 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1899458 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1515458 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7248. Min Act: -0.0000

Data Index: 630666 (The Pile)

Max Activating Token Index: 124

Text #7

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1218031 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6771. Min Act: -0.0000

Data Index: 281117 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.5752. Min Act: -0.0000

Data Index: 923955 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1637570 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1215864 (The Pile)

Max Activating Token Index: 72

Text #12

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1185474 (The Pile)

Max Activating Token Index: 325

Text #13

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6037. Min Act: -0.0000

Data Index: 848191 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6409. Min Act: -0.0000

Data Index: 61473 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6967. Min Act: -0.0000

Data Index: 906001 (The Pile)

Max Activating Token Index: 637

Text #16

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1069390 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.5823. Min Act: -0.0000

Data Index: 421111 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.5993. Min Act: -0.0000

Data Index: 131695 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1018822 (The Pile)

Max Activating Token Index: 978