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

Dataset: The Pile

Neuron 557 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.7110. Min Act: -0.0000

Data Index: 990842 (The Pile)

Max Activating Token Index: 857

Text #1

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.8236. Min Act: -0.0000

Data Index: 42360 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.8264. Min Act: -0.0000

Data Index: 626892 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.4996. Min Act: -0.0000

Data Index: 624797 (The Pile)

Max Activating Token Index: 479

Text #4

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.3832. Min Act: -0.0000

Data Index: 642916 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.2822. Min Act: -0.0000

Data Index: 1286230 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.2871. Min Act: -0.0000

Data Index: 1307236 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.3489. Min Act: -0.0000

Data Index: 596902 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.3056. Min Act: -0.0000

Data Index: 514919 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.1468. Min Act: -0.0000

Data Index: 1194220 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.4527. Min Act: -0.0000

Data Index: 1128128 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.2378. Min Act: -0.0000

Data Index: 234115 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.1805. Min Act: -0.0000

Data Index: 591205 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.3547. Min Act: -0.0000

Data Index: 943472 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.3199. Min Act: -0.0000

Data Index: 1098297 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.0213. Min Act: -0.0000

Data Index: 1768045 (The Pile)

Max Activating Token Index: 812

Text #16

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.1510. Min Act: -0.0000

Data Index: 1256763 (The Pile)

Max Activating Token Index: 943

Text #17

Max Range: 3.8264. Min Range: -3.8264

Max Act: 3.0351. Min Act: -0.0000

Data Index: 930811 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 3.8264. Min Range: -3.8264

Max Act: 2.8803. Min Act: -0.0000

Data Index: 1360226 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 3.8264. Min Range: -3.8264

Max Act: 2.8866. Min Act: -0.0000

Data Index: 1812868 (The Pile)

Max Activating Token Index: 727