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

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

Neuron 6127 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: 4.5817. Min Range: -4.5817

Max Act: 4.5815. Min Act: -0.0000

Data Index: 1468364 (Python Code)

Max Activating Token Index: 302

Text #1

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.5817. Min Act: -0.0000

Data Index: 1498340 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.8009. Min Act: -0.0000

Data Index: 1611762 (Python Code)

Max Activating Token Index: 229

Text #3

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.0176. Min Act: -0.0000

Data Index: 1464437 (Python Code)

Max Activating Token Index: 121

Text #4

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.6502. Min Act: -0.0000

Data Index: 1430798 (Python Code)

Max Activating Token Index: 235

Text #5

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.7306. Min Act: -0.0000

Data Index: 1632809 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.6944. Min Act: -0.0000

Data Index: 1448658 (Python Code)

Max Activating Token Index: 306

Text #7

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.8596. Min Act: -0.0000

Data Index: 1591639 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.8235. Min Act: -0.0000

Data Index: 1404030 (Python Code)

Max Activating Token Index: 192

Text #9

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.4348. Min Act: -0.0000

Data Index: 1420577 (Python Code)

Max Activating Token Index: 172

Text #10

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.3881. Min Act: -0.0000

Data Index: 1632051 (Python Code)

Max Activating Token Index: 356

Text #11

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.6670. Min Act: -0.0000

Data Index: 1513222 (Python Code)

Max Activating Token Index: 215

Text #12

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.2991. Min Act: -0.0000

Data Index: 1421618 (Python Code)

Max Activating Token Index: 133

Text #13

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.3097. Min Act: -0.0000

Data Index: 1633947 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.2623. Min Act: -0.0000

Data Index: 1396695 (Python Code)

Max Activating Token Index: 153

Text #15

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.4035. Min Act: -0.0000

Data Index: 1478713 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.7259. Min Act: -0.0000

Data Index: 1395008 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.3723. Min Act: -0.0000

Data Index: 1493937 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.0668. Min Act: -0.0000

Data Index: 1596981 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 4.5817. Min Range: -4.5817

Max Act: 3.3206. Min Act: -0.0000

Data Index: 1611241 (Python Code)

Max Activating Token Index: 247