Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2067 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1215411 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.3232. Min Act: -0.0000

Data Index: 638060 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2878. Min Act: -0.0000

Data Index: 856094 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2882. Min Act: -0.0000

Data Index: 951694 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1116730 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2692. Min Act: -0.0001

Data Index: 246032 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2811. Min Act: -0.0001

Data Index: 1254162 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2662. Min Act: -0.0001

Data Index: 1353570 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2784. Min Act: -0.0001

Data Index: 977686 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2614. Min Act: -0.0000

Data Index: 799323 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2402. Min Act: -0.0001

Data Index: 856444 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1089834 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2519. Min Act: -0.0001

Data Index: 873459 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2342. Min Act: -0.0001

Data Index: 559533 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1309813 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2404. Min Act: -0.0000

Data Index: 147508 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2236. Min Act: -0.0001

Data Index: 19779 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2450. Min Act: -0.0000

Data Index: 602635 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2342. Min Act: -0.0000

Data Index: 762506 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2258. Min Act: -0.0001

Data Index: 457188 (C4 (Web Text))

Max Activating Token Index: 968