Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1107 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.8452. Min Act: -0.0000

Data Index: 147240 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1083869 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.8337. Min Act: -0.0000

Data Index: 966850 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7283. Min Act: -0.0000

Data Index: 933473 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1104932 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6312. Min Act: -0.0000

Data Index: 172229 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1177966 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6236. Min Act: -0.0000

Data Index: 210878 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6154. Min Act: -0.0000

Data Index: 885339 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1204822 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6010. Min Act: -0.0000

Data Index: 167717 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.5999. Min Act: -0.0000

Data Index: 536443 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.5862. Min Act: -0.0000

Data Index: 937500 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.5908. Min Act: -0.0000

Data Index: 132531 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.5694. Min Act: -0.0000

Data Index: 835598 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.5837. Min Act: -0.0000

Data Index: 634927 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.5587. Min Act: -0.0000

Data Index: 917201 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1149501 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6078. Min Act: -0.0000

Data Index: 328334 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.5627. Min Act: -0.0000

Data Index: 748319 (C4 (Web Text))

Max Activating Token Index: 308