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

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

Neuron 3928 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.7596. Min Act: -0.0000

Data Index: 552793 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6668. Min Act: -0.0000

Data Index: 480258 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.5619. Min Act: -0.0000

Data Index: 1220094 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.4425. Min Act: -0.0000

Data Index: 593688 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.5104. Min Act: -0.0000

Data Index: 99577 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.4057. Min Act: -0.0000

Data Index: 923569 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.4955. Min Act: -0.0000

Data Index: 5408 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.3749. Min Act: -0.0000

Data Index: 835935 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.3820. Min Act: -0.0000

Data Index: 997151 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.2159. Min Act: -0.0000

Data Index: 1517705 (Python Code)

Max Activating Token Index: 231

Text #10

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.3110. Min Act: -0.0000

Data Index: 127747 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.3122. Min Act: -0.0000

Data Index: 11401 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1467661 (Python Code)

Max Activating Token Index: 383

Text #13

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1059864 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.2224. Min Act: -0.0000

Data Index: 693765 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1413272 (Python Code)

Max Activating Token Index: 226

Text #16

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1509823 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.2228. Min Act: -0.0000

Data Index: 240147 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.2057. Min Act: -0.0000

Data Index: 1422839 (Python Code)

Max Activating Token Index: 676

Text #19

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.3407. Min Act: -0.0000

Data Index: 88414 (C4 (Web Text))

Max Activating Token Index: 795