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

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

Neuron 3394 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8186. Min Range: -4.8186

Max Act: 4.8186. Min Act: -0.0001

Data Index: 317219 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.8698. Min Act: -0.0001

Data Index: 818306 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.9335. Min Act: -0.0001

Data Index: 1011853 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.6619. Min Act: -0.0001

Data Index: 496339 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.3886. Min Act: -0.0001

Data Index: 1565798 (Python Code)

Max Activating Token Index: 39

Text #5

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.5249. Min Act: -0.0001

Data Index: 832283 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.3012. Min Act: -0.0001

Data Index: 1469276 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.1468. Min Act: -0.0001

Data Index: 1489544 (Python Code)

Max Activating Token Index: 301

Text #8

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.0770. Min Act: -0.0001

Data Index: 1654665 (Python Code)

Max Activating Token Index: 381

Text #9

Max Range: 4.8186. Min Range: -4.8186

Max Act: 2.9468. Min Act: -0.0001

Data Index: 1529233 (Python Code)

Max Activating Token Index: 294

Text #10

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.0304. Min Act: -0.0001

Data Index: 1378292 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.0099. Min Act: -0.0001

Data Index: 1648440 (Python Code)

Max Activating Token Index: 533

Text #12

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.0017. Min Act: -0.0001

Data Index: 1586987 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 4.8186. Min Range: -4.8186

Max Act: 2.9657. Min Act: -0.0001

Data Index: 1462154 (Python Code)

Max Activating Token Index: 538

Text #14

Max Range: 4.8186. Min Range: -4.8186

Max Act: 2.9522. Min Act: -0.0001

Data Index: 1468831 (Python Code)

Max Activating Token Index: 487

Text #15

Max Range: 4.8186. Min Range: -4.8186

Max Act: 2.9066. Min Act: -0.0001

Data Index: 1572538 (Python Code)

Max Activating Token Index: 420

Text #16

Max Range: 4.8186. Min Range: -4.8186

Max Act: 2.7721. Min Act: -0.0001

Data Index: 1447101 (Python Code)

Max Activating Token Index: 272

Text #17

Max Range: 4.8186. Min Range: -4.8186

Max Act: 2.8875. Min Act: -0.0001

Data Index: 1539620 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 4.8186. Min Range: -4.8186

Max Act: 2.8601. Min Act: -0.0001

Data Index: 500407 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 4.8186. Min Range: -4.8186

Max Act: 3.0146. Min Act: -0.0001

Data Index: 1559425 (Python Code)

Max Activating Token Index: 638