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

Dataset: The Pile

Neuron 1619 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.8457. Min Act: -0.0000

Data Index: 1560940 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.9114. Min Act: -0.0000

Data Index: 1335524 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.7090. Min Act: -0.0000

Data Index: 385195 (The Pile)

Max Activating Token Index: 740

Text #3

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.5442. Min Act: -0.0000

Data Index: 33445 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.5634. Min Act: -0.0000

Data Index: 170190 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.3913. Min Act: -0.0000

Data Index: 796538 (The Pile)

Max Activating Token Index: 485

Text #6

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1150920 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.3810. Min Act: -0.0000

Data Index: 1021808 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.2621. Min Act: -0.0000

Data Index: 291215 (The Pile)

Max Activating Token Index: 634

Text #9

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.3687. Min Act: -0.0000

Data Index: 1785923 (The Pile)

Max Activating Token Index: 512

Text #10

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1297977 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.3348. Min Act: -0.0000

Data Index: 173697 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.2956. Min Act: -0.0000

Data Index: 548531 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.4108. Min Act: -0.0000

Data Index: 926642 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.2507. Min Act: -0.0000

Data Index: 192671 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.3994. Min Act: -0.0000

Data Index: 664762 (The Pile)

Max Activating Token Index: 665

Text #16

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.3061. Min Act: -0.0000

Data Index: 39997 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.3079. Min Act: -0.0000

Data Index: 72055 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1794146 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 1.9114. Min Range: -1.9114

Max Act: 1.3432. Min Act: -0.0000

Data Index: 1629744 (The Pile)

Max Activating Token Index: 506