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

Dataset: The Pile

Neuron 3145 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: 1.8524. Min Range: -1.8524

Max Act: 1.8524. Min Act: -0.0000

Data Index: 1280127 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.7556. Min Act: -0.0000

Data Index: 1072753 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.6003. Min Act: -0.0000

Data Index: 404857 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.4246. Min Act: -0.0000

Data Index: 1846475 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.4715. Min Act: -0.0000

Data Index: 400027 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.5961. Min Act: -0.0000

Data Index: 786753 (The Pile)

Max Activating Token Index: 309

Text #6

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1371832 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1842569 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.3789. Min Act: -0.0000

Data Index: 1040112 (The Pile)

Max Activating Token Index: 327

Text #9

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.4165. Min Act: -0.0000

Data Index: 1925415 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.3673. Min Act: -0.0000

Data Index: 313260 (The Pile)

Max Activating Token Index: 82

Text #11

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1252327 (The Pile)

Max Activating Token Index: 792

Text #12

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1484966 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.2743. Min Act: -0.0000

Data Index: 987422 (The Pile)

Max Activating Token Index: 153

Text #14

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.4186. Min Act: -0.0000

Data Index: 1736900 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.3091. Min Act: -0.0000

Data Index: 1375708 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.2472. Min Act: -0.0000

Data Index: 167998 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1130061 (The Pile)

Max Activating Token Index: 192

Text #18

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1470071 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 1.8524. Min Range: -1.8524

Max Act: 1.2067. Min Act: -0.0000

Data Index: 1690477 (The Pile)

Max Activating Token Index: 635