Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1886 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.0022. Min Range: -4.0022

Max Act: 4.0022. Min Act: -0.0001

Data Index: 426573 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 4.0022. Min Range: -4.0022

Max Act: 3.5256. Min Act: -0.0001

Data Index: 552373 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.7581. Min Act: -0.0000

Data Index: 503908 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.7375. Min Act: -0.0001

Data Index: 378907 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.6184. Min Act: -0.0001

Data Index: 1167613 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.4628. Min Act: -0.0001

Data Index: 1062168 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.5170. Min Act: -0.0001

Data Index: 383404 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.4956. Min Act: -0.0001

Data Index: 339752 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.4834. Min Act: -0.0001

Data Index: 18700 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.4096. Min Act: -0.0001

Data Index: 659182 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.4503. Min Act: -0.0001

Data Index: 610473 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.5112. Min Act: -0.0001

Data Index: 1140954 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.4429. Min Act: -0.0000

Data Index: 1269608 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.4963. Min Act: -0.0001

Data Index: 601683 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.4349. Min Act: -0.0001

Data Index: 121745 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.3821. Min Act: -0.0001

Data Index: 826309 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.2647. Min Act: -0.0000

Data Index: 77340 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.3837. Min Act: -0.0000

Data Index: 793150 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.4201. Min Act: -0.0001

Data Index: 1240406 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 4.0022. Min Range: -4.0022

Max Act: 2.3169. Min Act: -0.0000

Data Index: 736631 (C4 (Web Text))

Max Activating Token Index: 192