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

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

Neuron 2673 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3325. Min Range: -2.3325

Max Act: 2.3325. Min Act: -0.0000

Data Index: 779975 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.8839. Min Act: -0.0000

Data Index: 396624 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.7169. Min Act: -0.0000

Data Index: 986473 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1308449 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.5875. Min Act: -0.0000

Data Index: 881420 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.6509. Min Act: -0.0000

Data Index: 1148487 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.5599. Min Act: -0.0000

Data Index: 248267 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.5418. Min Act: -0.0000

Data Index: 740809 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.4855. Min Act: -0.0000

Data Index: 711631 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.4798. Min Act: -0.0000

Data Index: 1227087 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.4030. Min Act: -0.0000

Data Index: 328315 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.4283. Min Act: -0.0000

Data Index: 490883 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.3476. Min Act: -0.0000

Data Index: 878396 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.2509. Min Act: -0.0000

Data Index: 705362 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.4067. Min Act: -0.0000

Data Index: 673906 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.3158. Min Act: -0.0000

Data Index: 276139 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.2883. Min Act: -0.0000

Data Index: 720899 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.2819. Min Act: -0.0000

Data Index: 162738 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.3544. Min Act: -0.0000

Data Index: 961599 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 2.3325. Min Range: -2.3325

Max Act: 1.2482. Min Act: -0.0000

Data Index: 1035111 (C4 (Web Text))

Max Activating Token Index: 583