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

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

Neuron 658 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: 5.1915. Min Range: -5.1915

Max Act: 5.1915. Min Act: -0.0001

Data Index: 1232941 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 5.1915. Min Range: -5.1915

Max Act: 4.2892. Min Act: -0.0001

Data Index: 359656 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 5.1915. Min Range: -5.1915

Max Act: 3.7021. Min Act: -0.0001

Data Index: 910575 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 5.1915. Min Range: -5.1915

Max Act: 3.0860. Min Act: -0.0001

Data Index: 945668 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 5.1915. Min Range: -5.1915

Max Act: 3.6548. Min Act: -0.0001

Data Index: 571362 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 5.1915. Min Range: -5.1915

Max Act: 3.7140. Min Act: -0.0001

Data Index: 1298272 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 5.1915. Min Range: -5.1915

Max Act: 3.3438. Min Act: -0.0001

Data Index: 1161374 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 5.1915. Min Range: -5.1915

Max Act: 3.0266. Min Act: -0.0001

Data Index: 942654 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 5.1915. Min Range: -5.1915

Max Act: 2.9936. Min Act: -0.0001

Data Index: 1115299 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 5.1915. Min Range: -5.1915

Max Act: 2.8550. Min Act: -0.0001

Data Index: 809080 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 5.1915. Min Range: -5.1915

Max Act: 2.6250. Min Act: -0.0001

Data Index: 388786 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 5.1915. Min Range: -5.1915

Max Act: 2.7456. Min Act: -0.0001

Data Index: 1024638 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 5.1915. Min Range: -5.1915

Max Act: 3.0045. Min Act: -0.0001

Data Index: 835308 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 5.1915. Min Range: -5.1915

Max Act: 2.8225. Min Act: -0.0001

Data Index: 281310 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 5.1915. Min Range: -5.1915

Max Act: 2.6855. Min Act: -0.0001

Data Index: 998125 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 5.1915. Min Range: -5.1915

Max Act: 2.9560. Min Act: -0.0001

Data Index: 580707 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 5.1915. Min Range: -5.1915

Max Act: 2.8049. Min Act: -0.0001

Data Index: 195810 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 5.1915. Min Range: -5.1915

Max Act: 2.7757. Min Act: -0.0001

Data Index: 650075 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 5.1915. Min Range: -5.1915

Max Act: 3.0649. Min Act: -0.0001

Data Index: 336052 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 5.1915. Min Range: -5.1915

Max Act: 2.6028. Min Act: -0.0001

Data Index: 732076 (C4 (Web Text))

Max Activating Token Index: 225