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

Dataset: The Pile

Neuron 2719 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: 1.1819. Min Range: -1.1819

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1188261 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.1718. Min Act: -0.0000

Data Index: 1283642 (The Pile)

Max Activating Token Index: 873

Text #2

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8965. Min Act: -0.0000

Data Index: 316694 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1021823 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1053109 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1984039 (The Pile)

Max Activating Token Index: 266

Text #6

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8956. Min Act: -0.0000

Data Index: 510511 (The Pile)

Max Activating Token Index: 917

Text #7

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1553282 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7755. Min Act: -0.0000

Data Index: 981689 (The Pile)

Max Activating Token Index: 5

Text #9

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1639224 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1081459 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1975755 (The Pile)

Max Activating Token Index: 196

Text #12

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7684. Min Act: -0.0000

Data Index: 787344 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1907990 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7407. Min Act: -0.0000

Data Index: 89607 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7887. Min Act: -0.0000

Data Index: 842564 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1312447 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1020581 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7944. Min Act: -0.0000

Data Index: 143911 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1912850 (The Pile)

Max Activating Token Index: 783