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

Dataset: The Pile

Neuron 1287 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.7610. Min Act: -0.0000

Data Index: 1373969 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.6134. Min Act: -0.0000

Data Index: 1163668 (The Pile)

Max Activating Token Index: 181

Text #2

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.7324. Min Act: -0.0000

Data Index: 826218 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.5891. Min Act: -0.0000

Data Index: 792657 (The Pile)

Max Activating Token Index: 181

Text #4

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.4623. Min Act: -0.0000

Data Index: 1541180 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.4013. Min Act: -0.0000

Data Index: 945324 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.1936. Min Act: -0.0000

Data Index: 1227292 (The Pile)

Max Activating Token Index: 694

Text #7

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.0809. Min Act: -0.0000

Data Index: 503022 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.2251. Min Act: -0.0000

Data Index: 1522525 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.2173. Min Act: -0.0000

Data Index: 1367596 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.2120. Min Act: -0.0000

Data Index: 977265 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.3752. Min Act: -0.0000

Data Index: 1613121 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.1905. Min Act: -0.0000

Data Index: 1738017 (The Pile)

Max Activating Token Index: 624

Text #13

Max Range: 5.7610. Min Range: -5.7610

Max Act: 4.9804. Min Act: -0.0000

Data Index: 893542 (The Pile)

Max Activating Token Index: 466

Text #14

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.1443. Min Act: -0.0000

Data Index: 1541557 (The Pile)

Max Activating Token Index: 331

Text #15

Max Range: 5.7610. Min Range: -5.7610

Max Act: 4.9545. Min Act: -0.0000

Data Index: 484608 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.1222. Min Act: -0.0000

Data Index: 380692 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 5.7610. Min Range: -5.7610

Max Act: 4.9185. Min Act: -0.0000

Data Index: 760406 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 5.7610. Min Range: -5.7610

Max Act: 5.0801. Min Act: -0.0000

Data Index: 1747544 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 5.7610. Min Range: -5.7610

Max Act: 4.8585. Min Act: -0.0000

Data Index: 470492 (The Pile)

Max Activating Token Index: 444