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

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

Neuron 4486 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.9114. Min Act: -0.0000

Data Index: 689924 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1299593 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.7639. Min Act: -0.0000

Data Index: 263691 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1013659 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.7659. Min Act: -0.0000

Data Index: 874469 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1152185 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6969. Min Act: -0.0000

Data Index: 143247 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.5345. Min Act: -0.0000

Data Index: 821229 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6252. Min Act: -0.0000

Data Index: 620700 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.5538. Min Act: -0.0000

Data Index: 102748 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.4884. Min Act: -0.0000

Data Index: 782581 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1264978 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1500344 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.4497. Min Act: -0.0000

Data Index: 118436 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.4261. Min Act: -0.0000

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.4503. Min Act: -0.0000

Data Index: 639947 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.4181. Min Act: -0.0000

Data Index: 444318 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1067058 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.4300. Min Act: -0.0000

Data Index: 721926 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1162336 (C4 (Web Text))

Max Activating Token Index: 493