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

Dataset: The Pile

Neuron 2308 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: 0.7187. Min Range: -0.7187

Max Act: 0.7187. Min Act: -0.0000

Data Index: 790913 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1580398 (The Pile)

Max Activating Token Index: 765

Text #2

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1688293 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5794. Min Act: -0.0000

Data Index: 121025 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1769918 (The Pile)

Max Activating Token Index: 692

Text #5

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5453. Min Act: -0.0000

Data Index: 637693 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5438. Min Act: -0.0000

Data Index: 583889 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1911510 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1955275 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1189169 (The Pile)

Max Activating Token Index: 926

Text #10

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1574241 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4263. Min Act: -0.0000

Data Index: 755509 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1152798 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1105683 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1353190 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1773975 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1438635 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1670551 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1231110 (The Pile)

Max Activating Token Index: 535

Text #19

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5011. Min Act: -0.0000

Data Index: 35518 (The Pile)

Max Activating Token Index: 282