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

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

Neuron 1141 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4270. Min Range: -2.4270

Max Act: 2.4270. Min Act: -0.0000

Data Index: 1249503 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.8768. Min Act: -0.0000

Data Index: 254542 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.7998. Min Act: -0.0000

Data Index: 295838 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.7941. Min Act: -0.0000

Data Index: 1645998 (Python Code)

Max Activating Token Index: 392

Text #4

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.8044. Min Act: -0.0000

Data Index: 1299129 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.6927. Min Act: -0.0000

Data Index: 214713 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.6840. Min Act: -0.0000

Data Index: 1283149 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.6595. Min Act: -0.0000

Data Index: 1102583 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.6570. Min Act: -0.0000

Data Index: 1147520 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.6572. Min Act: -0.0000

Data Index: 801747 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.5333. Min Act: -0.0000

Data Index: 403491 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.6090. Min Act: -0.0000

Data Index: 104 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.5661. Min Act: -0.0000

Data Index: 625769 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.7069. Min Act: -0.0000

Data Index: 531980 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.6046. Min Act: -0.0000

Data Index: 1136131 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1335250 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.5798. Min Act: -0.0000

Data Index: 1028690 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.5758. Min Act: -0.0000

Data Index: 725650 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.6357. Min Act: -0.0000

Data Index: 891429 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 2.4270. Min Range: -2.4270

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1065908 (C4 (Web Text))

Max Activating Token Index: 326