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

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

Neuron 4085 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.7148. Min Act: -0.0000

Data Index: 1344083 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.5109. Min Act: -0.0000

Data Index: 1088248 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4631. Min Act: -0.0000

Data Index: 296075 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.5407. Min Act: -0.0000

Data Index: 688659 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4507. Min Act: -0.0000

Data Index: 889083 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.5353. Min Act: -0.0000

Data Index: 95026 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.5216. Min Act: -0.0000

Data Index: 245402 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4318. Min Act: -0.0000

Data Index: 282016 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.5086. Min Act: -0.0000

Data Index: 449359 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.5044. Min Act: -0.0000

Data Index: 13994 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4137. Min Act: -0.0000

Data Index: 263274 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4917. Min Act: -0.0001

Data Index: 784394 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4880. Min Act: -0.0000

Data Index: 702577 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4016. Min Act: -0.0000

Data Index: 951515 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4793. Min Act: -0.0000

Data Index: 347255 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4740. Min Act: -0.0000

Data Index: 590230 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4694. Min Act: -0.0000

Data Index: 674903 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4028. Min Act: -0.0000

Data Index: 471738 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4501. Min Act: -0.0000

Data Index: 822127 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.3728. Min Act: -0.0000

Data Index: 534697 (C4 (Web Text))

Max Activating Token Index: 312