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

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

Neuron 5989 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: 2.3428. Min Range: -2.3428

Max Act: 2.2776. Min Act: -0.0000

Data Index: 616130 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 2.3428. Min Range: -2.3428

Max Act: 2.1486. Min Act: -0.0000

Data Index: 824335 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 2.3428. Min Range: -2.3428

Max Act: 2.3428. Min Act: -0.0000

Data Index: 1195481 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 2.3428. Min Range: -2.3428

Max Act: 2.1845. Min Act: -0.0000

Data Index: 234082 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 2.3428. Min Range: -2.3428

Max Act: 2.1456. Min Act: -0.0000

Data Index: 533087 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 2.3428. Min Range: -2.3428

Max Act: 2.2683. Min Act: -0.0000

Data Index: 875014 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 2.3428. Min Range: -2.3428

Max Act: 2.2183. Min Act: -0.0000

Data Index: 906789 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 2.3428. Min Range: -2.3428

Max Act: 2.0583. Min Act: -0.0000

Data Index: 1485626 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 2.3428. Min Range: -2.3428

Max Act: 2.0425. Min Act: -0.0000

Data Index: 925205 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 2.3428. Min Range: -2.3428

Max Act: 2.0050. Min Act: -0.0000

Data Index: 1269802 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 2.3428. Min Range: -2.3428

Max Act: 1.8915. Min Act: -0.0000

Data Index: 187038 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 2.3428. Min Range: -2.3428

Max Act: 1.9863. Min Act: -0.0000

Data Index: 1173059 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 2.3428. Min Range: -2.3428

Max Act: 1.9410. Min Act: -0.0000

Data Index: 335019 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 2.3428. Min Range: -2.3428

Max Act: 1.9271. Min Act: -0.0000

Data Index: 569696 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 2.3428. Min Range: -2.3428

Max Act: 1.7958. Min Act: -0.0000

Data Index: 743095 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 2.3428. Min Range: -2.3428

Max Act: 1.9488. Min Act: 0.0000

Data Index: 1198262 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 2.3428. Min Range: -2.3428

Max Act: 1.7320. Min Act: -0.0000

Data Index: 267375 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 2.3428. Min Range: -2.3428

Max Act: 1.7899. Min Act: -0.0000

Data Index: 144401 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 2.3428. Min Range: -2.3428

Max Act: 1.6449. Min Act: 0.0000

Data Index: 401589 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 2.3428. Min Range: -2.3428

Max Act: 1.7153. Min Act: -0.0000

Data Index: 1548572 (Python Code)

Max Activating Token Index: 322