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

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

Neuron 5994 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: 1.1953. Min Range: -1.1953

Max Act: 1.1953. Min Act: -0.0000

Data Index: 407460 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1094761 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.0059. Min Act: -0.0000

Data Index: 79273 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9897. Min Act: -0.0000

Data Index: 777903 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9633. Min Act: -0.0000

Data Index: 906780 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9869. Min Act: -0.0000

Data Index: 145254 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9498. Min Act: -0.0000

Data Index: 729686 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1306518 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8414. Min Act: -0.0000

Data Index: 207827 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9346. Min Act: -0.0000

Data Index: 490341 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1298131 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8790. Min Act: -0.0000

Data Index: 647330 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8354. Min Act: 0.0000

Data Index: 694223 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9046. Min Act: -0.0000

Data Index: 633648 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9386. Min Act: -0.0000

Data Index: 285313 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8674. Min Act: -0.0000

Data Index: 101248 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1274960 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1219304 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8478. Min Act: -0.0000

Data Index: 827620 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8543. Min Act: -0.0000

Data Index: 448823 (C4 (Web Text))

Max Activating Token Index: 857