Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2156 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.3077. Min Act: -0.0000

Data Index: 162669 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.3008. Min Act: -0.0000

Data Index: 939291 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2841. Min Act: -0.0000

Data Index: 495094 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2635. Min Act: -0.0000

Data Index: 727412 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2679. Min Act: -0.0000

Data Index: 202184 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2824. Min Act: -0.0000

Data Index: 124145 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2525. Min Act: -0.0000

Data Index: 28769 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1279816 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2349. Min Act: -0.0000

Data Index: 560428 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1341051 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1342176 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2335. Min Act: -0.0000

Data Index: 291793 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2410. Min Act: -0.0000

Data Index: 969424 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1286960 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2370. Min Act: -0.0000

Data Index: 584238 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1252105 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1153483 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1181510 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2143. Min Act: -0.0000

Data Index: 96968 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2139. Min Act: -0.0000

Data Index: 197178 (C4 (Web Text))

Max Activating Token Index: 769