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

Dataset: The Pile

Neuron 4014 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.5447. Min Act: -0.0000

Data Index: 592375 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.6780. Min Act: -0.0000

Data Index: 1002952 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.5907. Min Act: -0.0000

Data Index: 1027725 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.5374. Min Act: -0.0000

Data Index: 1458683 (The Pile)

Max Activating Token Index: 484

Text #4

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.4939. Min Act: -0.0000

Data Index: 449631 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.4849. Min Act: -0.0000

Data Index: 1340337 (The Pile)

Max Activating Token Index: 419

Text #6

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1951990 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.3697. Min Act: -0.0000

Data Index: 410860 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.6235. Min Act: -0.0000

Data Index: 1411357 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.5273. Min Act: -0.0000

Data Index: 948645 (The Pile)

Max Activating Token Index: 124

Text #10

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.4281. Min Act: -0.0000

Data Index: 1062520 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.3281. Min Act: -0.0000

Data Index: 759791 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.3274. Min Act: -0.0000

Data Index: 705245 (The Pile)

Max Activating Token Index: 579

Text #13

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.4107. Min Act: -0.0000

Data Index: 1954196 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.3906. Min Act: -0.0000

Data Index: 1093502 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1376033 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.3906. Min Act: -0.0000

Data Index: 1185628 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1058391 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.2925. Min Act: -0.0000

Data Index: 857832 (The Pile)

Max Activating Token Index: 716

Text #19

Max Range: 1.6780. Min Range: -1.6780

Max Act: 1.3689. Min Act: -0.0000

Data Index: 1594895 (The Pile)

Max Activating Token Index: 242