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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3611 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.7118. Min Act: -0.0000

Data Index: 182901 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.6919. Min Act: -0.0000

Data Index: 646414 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.5820. Min Act: -0.0000

Data Index: 294141 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.5956. Min Act: -0.0000

Data Index: 478286 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.5157. Min Act: -0.0000

Data Index: 432785 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.5296. Min Act: -0.0000

Data Index: 519940 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.5100. Min Act: -0.0000

Data Index: 256393 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.5277. Min Act: -0.0000

Data Index: 339121 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1111807 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.5329. Min Act: -0.0000

Data Index: 235807 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1041252 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.4435. Min Act: -0.0000

Data Index: 760883 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.4487. Min Act: -0.0000

Data Index: 377733 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.4723. Min Act: -0.0000

Data Index: 595417 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.4383. Min Act: -0.0000

Data Index: 912604 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1091034 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.4266. Min Act: -0.0000

Data Index: 671904 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1015890 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.4461. Min Act: -0.0000

Data Index: 639552 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.7118. Min Range: -0.7118

Max Act: 0.3978. Min Act: -0.0000

Data Index: 379217 (C4 (Web Text))

Max Activating Token Index: 674