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

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

Neuron 3838 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4215. Min Range: -1.4215

Max Act: 1.4215. Min Act: -0.0000

Data Index: 1264762 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.4215. Min Range: -1.4215

Max Act: 1.3061. Min Act: -0.0000

Data Index: 656803 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 1.4215. Min Range: -1.4215

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1330898 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.4215. Min Range: -1.4215

Max Act: 1.1063. Min Act: -0.0000

Data Index: 485738 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 1.4215. Min Range: -1.4215

Max Act: 1.0112. Min Act: -0.0000

Data Index: 351266 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.4215. Min Range: -1.4215

Max Act: 1.0620. Min Act: -0.0000

Data Index: 264380 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.4215. Min Range: -1.4215

Max Act: 1.0192. Min Act: 0.0000

Data Index: 1530590 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1598075 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1487278 (Python Code)

Max Activating Token Index: 493

Text #9

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1315450 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.9488. Min Act: 0.0000

Data Index: 1445656 (Python Code)

Max Activating Token Index: 219

Text #11

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.9525. Min Act: -0.0000

Data Index: 540356 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.9324. Min Act: -0.0000

Data Index: 188345 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.9218. Min Act: -0.0000

Data Index: 619715 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.9081. Min Act: -0.0000

Data Index: 188902 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.8888. Min Act: -0.0000

Data Index: 327446 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.8132. Min Act: -0.0000

Data Index: 423921 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.8771. Min Act: -0.0000

Data Index: 162809 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1546609 (Python Code)

Max Activating Token Index: 559

Text #19

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.8535. Min Act: -0.0000

Data Index: 879902 (C4 (Web Text))

Max Activating Token Index: 198