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

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

Neuron 1992 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1497300 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1410623 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1376304 (Python Code)

Max Activating Token Index: 465

Text #3

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1512274 (Python Code)

Max Activating Token Index: 558

Text #4

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1051164 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1602849 (Python Code)

Max Activating Token Index: 213

Text #6

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1491428 (Python Code)

Max Activating Token Index: 801

Text #7

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1459479 (Python Code)

Max Activating Token Index: 120

Text #8

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1231816 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.3025. Min Act: -0.0000

Data Index: 176499 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1513684 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.3049. Min Act: -0.0000

Data Index: 516444 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1394711 (Python Code)

Max Activating Token Index: 140

Text #13

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1227332 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1569084 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1441535 (Python Code)

Max Activating Token Index: 723

Text #16

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1422044 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1386317 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1611951 (Python Code)

Max Activating Token Index: 668

Text #19

Max Range: 0.5181. Min Range: -0.5181

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1564745 (Python Code)

Max Activating Token Index: 638