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

Dataset: The Pile

Neuron 466 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: 0.4381. Min Range: -0.4381

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1436454 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.4069. Min Act: -0.0000

Data Index: 141657 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3852. Min Act: -0.0000

Data Index: 23902 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3778. Min Act: -0.0000

Data Index: 143753 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.4111. Min Act: -0.0000

Data Index: 475422 (The Pile)

Max Activating Token Index: 596

Text #5

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1356935 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3912. Min Act: -0.0000

Data Index: 481003 (The Pile)

Max Activating Token Index: 697

Text #7

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3233. Min Act: -0.0000

Data Index: 544612 (The Pile)

Max Activating Token Index: 184

Text #8

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3362. Min Act: -0.0000

Data Index: 593512 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1566954 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1530701 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1511976 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1320847 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1973151 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1995893 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2970. Min Act: -0.0000

Data Index: 642020 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3117. Min Act: -0.0000

Data Index: 209533 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3016. Min Act: -0.0000

Data Index: 970090 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1538832 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2806. Min Act: -0.0000

Data Index: 682461 (The Pile)

Max Activating Token Index: 445