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

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

Neuron 1105 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.3151. Min Act: -0.0001

Data Index: 696863 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.1935. Min Act: -0.0001

Data Index: 1238897 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.2048. Min Act: -0.0001

Data Index: 301005 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.1001. Min Act: -0.0001

Data Index: 904386 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.1111. Min Act: -0.0001

Data Index: 861865 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0730. Min Act: -0.0001

Data Index: 857171 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.1052. Min Act: -0.0001

Data Index: 923389 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0913. Min Act: -0.0001

Data Index: 1202385 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0655. Min Act: -0.0001

Data Index: 147278 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9892. Min Act: -0.0001

Data Index: 803225 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0163. Min Act: -0.0001

Data Index: 450311 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0105. Min Act: -0.0001

Data Index: 1210173 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0312. Min Act: -0.0001

Data Index: 1066482 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9736. Min Act: -0.0001

Data Index: 1267677 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9495. Min Act: -0.0001

Data Index: 221889 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0019. Min Act: -0.0001

Data Index: 335949 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9683. Min Act: -0.0001

Data Index: 184834 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9691. Min Act: -0.0001

Data Index: 712257 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9656. Min Act: -0.0001

Data Index: 463131 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9636. Min Act: -0.0001

Data Index: 1224087 (C4 (Web Text))

Max Activating Token Index: 8