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

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

Neuron 691 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: 1.8430. Min Range: -1.8430

Max Act: 1.8430. Min Act: -0.0000

Data Index: 1221103 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.5814. Min Act: -0.0000

Data Index: 127482 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.5697. Min Act: -0.0000

Data Index: 1357250 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4820. Min Act: -0.0000

Data Index: 291585 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4997. Min Act: -0.0000

Data Index: 373080 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4965. Min Act: -0.0000

Data Index: 443094 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4320. Min Act: -0.0000

Data Index: 459834 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3880. Min Act: -0.0000

Data Index: 401848 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1084451 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3113. Min Act: -0.0000

Data Index: 1009777 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3969. Min Act: -0.0000

Data Index: 889258 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.2811. Min Act: -0.0000

Data Index: 1287485 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3092. Min Act: -0.0000

Data Index: 343791 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3042. Min Act: -0.0000

Data Index: 90592 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.2854. Min Act: -0.0000

Data Index: 630966 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3134. Min Act: -0.0000

Data Index: 242799 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3295. Min Act: -0.0000

Data Index: 681730 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.2712. Min Act: -0.0000

Data Index: 737605 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.2055. Min Act: -0.0000

Data Index: 877457 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.2221. Min Act: -0.0000

Data Index: 671306 (C4 (Web Text))

Max Activating Token Index: 175