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

Dataset: The Pile

Neuron 3498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3159. Min Range: -1.3159

Max Act: 1.3159. Min Act: -0.0000

Data Index: 1682928 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 1.3159. Min Range: -1.3159

Max Act: 1.1439. Min Act: -0.0000

Data Index: 1962167 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1012436 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1309845 (The Pile)

Max Activating Token Index: 125

Text #4

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1711550 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1124762 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1049699 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.7227. Min Act: 0.0000

Data Index: 1154008 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.7223. Min Act: 0.0000

Data Index: 1341935 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1924461 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.7531. Min Act: -0.0000

Data Index: 866440 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.7019. Min Act: 0.0000

Data Index: 1292887 (The Pile)

Max Activating Token Index: 467

Text #12

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.7090. Min Act: 0.0000

Data Index: 1001777 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1028563 (The Pile)

Max Activating Token Index: 1008

Text #14

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.7203. Min Act: -0.0000

Data Index: 698119 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.6671. Min Act: -0.0000

Data Index: 437274 (The Pile)

Max Activating Token Index: 321

Text #16

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.6709. Min Act: 0.0000

Data Index: 1846714 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.6573. Min Act: -0.0000

Data Index: 918691 (The Pile)

Max Activating Token Index: 678

Text #18

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1674364 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1791117 (The Pile)

Max Activating Token Index: 818