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

Dataset: The Pile

Neuron 3053 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.6503. Min Act: -0.0000

Data Index: 457233 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.5309. Min Act: -0.0000

Data Index: 642153 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.5283. Min Act: -0.0000

Data Index: 1111627 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1355621 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1141402 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.4533. Min Act: -0.0000

Data Index: 1451348 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1785989 (The Pile)

Max Activating Token Index: 64

Text #7

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.3440. Min Act: -0.0000

Data Index: 389705 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.3819. Min Act: -0.0000

Data Index: 1820708 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1666172 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.4010. Min Act: -0.0000

Data Index: 161913 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2538. Min Act: -0.0000

Data Index: 1191534 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2439. Min Act: -0.0000

Data Index: 653813 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1864033 (The Pile)

Max Activating Token Index: 880

Text #14

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1487665 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2957. Min Act: -0.0000

Data Index: 108397 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2254. Min Act: -0.0000

Data Index: 882632 (The Pile)

Max Activating Token Index: 719

Text #17

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2073. Min Act: -0.0000

Data Index: 789711 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1302621 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1918488 (The Pile)

Max Activating Token Index: 984