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

Dataset: The Pile

Neuron 2549 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: 1.2137. Min Range: -1.2137

Max Act: 1.2137. Min Act: -0.0000

Data Index: 484436 (The Pile)

Max Activating Token Index: 350

Text #1

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1645516 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1107475 (The Pile)

Max Activating Token Index: 804

Text #3

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6783. Min Act: -0.0000

Data Index: 951959 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1179700 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6465. Min Act: -0.0000

Data Index: 361835 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1646847 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1793627 (The Pile)

Max Activating Token Index: 885

Text #8

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.5894. Min Act: -0.0000

Data Index: 302315 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6241. Min Act: -0.0000

Data Index: 246829 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6174. Min Act: -0.0000

Data Index: 399343 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.5990. Min Act: -0.0000

Data Index: 391672 (The Pile)

Max Activating Token Index: 167

Text #12

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6347. Min Act: -0.0000

Data Index: 854697 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1325044 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1242193 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6202. Min Act: -0.0000

Data Index: 440140 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.5984. Min Act: -0.0000

Data Index: 773579 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1065035 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1001924 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.5847. Min Act: -0.0000

Data Index: 905981 (The Pile)

Max Activating Token Index: 710