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

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

Neuron 2749 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: 5.6248. Min Range: -5.6248

Max Act: 5.6248. Min Act: 0.0000

Data Index: 437126 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 5.6248. Min Range: -5.6248

Max Act: 5.5597. Min Act: 0.0000

Data Index: 1279915 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 5.6248. Min Range: -5.6248

Max Act: 4.1560. Min Act: -0.0000

Data Index: 1277728 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 5.6248. Min Range: -5.6248

Max Act: 3.4550. Min Act: -0.0000

Data Index: 168622 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 5.6248. Min Range: -5.6248

Max Act: 3.4350. Min Act: -0.0000

Data Index: 728345 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 5.6248. Min Range: -5.6248

Max Act: 3.4814. Min Act: 0.0000

Data Index: 633416 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.8738. Min Act: 0.0000

Data Index: 195915 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.7170. Min Act: 0.0000

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.4915. Min Act: -0.0000

Data Index: 1044301 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.4940. Min Act: -0.0000

Data Index: 574038 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.4956. Min Act: -0.0000

Data Index: 354329 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.4845. Min Act: -0.0000

Data Index: 1191063 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.4629. Min Act: -0.0000

Data Index: 787575 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.4371. Min Act: -0.0000

Data Index: 791531 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.3267. Min Act: -0.0000

Data Index: 24206 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.5618. Min Act: 0.0000

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.4186. Min Act: 0.0000

Data Index: 931147 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.3925. Min Act: -0.0000

Data Index: 948421 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.2984. Min Act: -0.0000

Data Index: 185929 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 5.6248. Min Range: -5.6248

Max Act: 2.5428. Min Act: -0.0000

Data Index: 614386 (C4 (Web Text))

Max Activating Token Index: 635