Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 146 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.0663. Min Range: -1.0663

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1209423 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.8953. Min Act: -0.0001

Data Index: 209529 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.8772. Min Act: -0.0001

Data Index: 990885 (The Pile)

Max Activating Token Index: 744

Text #3

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7737. Min Act: -0.0000

Data Index: 759886 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7556. Min Act: -0.0000

Data Index: 438848 (The Pile)

Max Activating Token Index: 527

Text #5

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7050. Min Act: -0.0001

Data Index: 1875381 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1312627 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7330. Min Act: -0.0000

Data Index: 276739 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1627964 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6841. Min Act: -0.0000

Data Index: 430163 (The Pile)

Max Activating Token Index: 272

Text #10

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1107777 (The Pile)

Max Activating Token Index: 109

Text #11

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7214. Min Act: -0.0001

Data Index: 1105124 (The Pile)

Max Activating Token Index: 855

Text #12

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6936. Min Act: -0.0000

Data Index: 212111 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6506. Min Act: -0.0000

Data Index: 361935 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1500935 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1835736 (The Pile)

Max Activating Token Index: 923

Text #16

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6814. Min Act: -0.0000

Data Index: 266184 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1152346 (The Pile)

Max Activating Token Index: 144

Text #18

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1049431 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6394. Min Act: -0.0000

Data Index: 206356 (The Pile)

Max Activating Token Index: 731