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

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

Neuron 3602 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1309014 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.8075. Min Act: -0.0000

Data Index: 389094 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6755. Min Act: -0.0000

Data Index: 317942 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6797. Min Act: -0.0000

Data Index: 639647 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6691. Min Act: -0.0000

Data Index: 906203 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6547. Min Act: -0.0000

Data Index: 263766 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6061. Min Act: -0.0000

Data Index: 427199 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1339329 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1304073 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1341735 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6194. Min Act: -0.0000

Data Index: 744107 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6159. Min Act: -0.0000

Data Index: 176932 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1115413 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6096. Min Act: -0.0000

Data Index: 512388 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1117887 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6066. Min Act: -0.0000

Data Index: 161745 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5836. Min Act: -0.0000

Data Index: 286588 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5801. Min Act: -0.0000

Data Index: 429612 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5770. Min Act: -0.0000

Data Index: 539832 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1099474 (C4 (Web Text))

Max Activating Token Index: 817