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

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

Neuron 2704 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1222535 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.3568. Min Act: -0.0001

Data Index: 116616 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.2878. Min Act: -0.0000

Data Index: 775519 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.1249. Min Act: -0.0001

Data Index: 96013 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0788. Min Act: -0.0001

Data Index: 706697 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0083. Min Act: -0.0000

Data Index: 699258 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0337. Min Act: -0.0001

Data Index: 1121681 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0164. Min Act: -0.0001

Data Index: 216669 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0165. Min Act: -0.0001

Data Index: 885529 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9940. Min Act: -0.0001

Data Index: 1302422 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0461. Min Act: -0.0001

Data Index: 960875 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1383265 (Python Code)

Max Activating Token Index: 193

Text #12

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9654. Min Act: -0.0001

Data Index: 1176603 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9414. Min Act: -0.0001

Data Index: 7620 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0397. Min Act: -0.0001

Data Index: 12391 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9235. Min Act: -0.0001

Data Index: 1091385 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9225. Min Act: -0.0000

Data Index: 436232 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9675. Min Act: -0.0001

Data Index: 1110791 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1476308 (Python Code)

Max Activating Token Index: 752

Text #19

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1334874 (C4 (Web Text))

Max Activating Token Index: 909