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

Dataset: The Pile

Neuron 1392 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: 0.7439. Min Range: -0.7439

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1290665 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1874698 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.7136. Min Act: -0.0000

Data Index: 53339 (The Pile)

Max Activating Token Index: 883

Text #3

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1240836 (The Pile)

Max Activating Token Index: 84

Text #4

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5929. Min Act: -0.0000

Data Index: 580901 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5849. Min Act: -0.0000

Data Index: 709644 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5489. Min Act: -0.0000

Data Index: 348694 (The Pile)

Max Activating Token Index: 907

Text #7

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5759. Min Act: -0.0000

Data Index: 503599 (The Pile)

Max Activating Token Index: 347

Text #8

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5705. Min Act: -0.0000

Data Index: 258555 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1162354 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1153340 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5359. Min Act: -0.0000

Data Index: 152495 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5250. Min Act: -0.0000

Data Index: 57726 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1645448 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1992412 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5145. Min Act: -0.0000

Data Index: 129380 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4933. Min Act: -0.0000

Data Index: 818369 (The Pile)

Max Activating Token Index: 119

Text #17

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1263020 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1299987 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4815. Min Act: -0.0000

Data Index: 552852 (The Pile)

Max Activating Token Index: 777