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

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

Neuron 3629 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.4022. Min Act: -0.0001

Data Index: 283750 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3886. Min Act: -0.0000

Data Index: 723129 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3904. Min Act: -0.0000

Data Index: 353296 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3839. Min Act: -0.0000

Data Index: 891820 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3426. Min Act: -0.0001

Data Index: 18989 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3289. Min Act: 0.0000

Data Index: 1320378 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3456. Min Act: -0.0000

Data Index: 764949 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3320. Min Act: -0.0001

Data Index: 54416 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3259. Min Act: -0.0000

Data Index: 791718 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1022429 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3144. Min Act: -0.0001

Data Index: 281802 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3047. Min Act: -0.0000

Data Index: 705806 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3038. Min Act: -0.0000

Data Index: 254881 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3210. Min Act: -0.0001

Data Index: 520246 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1002211 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.2914. Min Act: -0.0000

Data Index: 470613 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1251232 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1177113 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3031. Min Act: -0.0000

Data Index: 757054 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.4022. Min Range: -0.4022

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1210557 (C4 (Web Text))

Max Activating Token Index: 577