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

Dataset: The Pile

Neuron 2898 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: 1.2226. Min Range: -1.2226

Max Act: 1.1586. Min Act: -0.0000

Data Index: 256592 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1928. Min Act: -0.0000

Data Index: 654160 (The Pile)

Max Activating Token Index: 400

Text #2

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1642. Min Act: -0.0000

Data Index: 841195 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.0443. Min Act: -0.0000

Data Index: 1268195 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.2226. Min Act: -0.0000

Data Index: 541126 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1601. Min Act: -0.0000

Data Index: 1479936 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.9427. Min Act: -0.0000

Data Index: 263691 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1182367 (The Pile)

Max Activating Token Index: 165

Text #8

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1995762 (The Pile)

Max Activating Token Index: 513

Text #9

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8791. Min Act: -0.0000

Data Index: 378882 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.9010. Min Act: -0.0000

Data Index: 649529 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1022905 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1931017 (The Pile)

Max Activating Token Index: 287

Text #13

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1900862 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1449150 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8356. Min Act: -0.0000

Data Index: 106788 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1581174 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1993306 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1910345 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1937042 (The Pile)

Max Activating Token Index: 650