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

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

Neuron 40 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.7229. Min Act: -0.0000

Data Index: 1399439 (Python Code)

Max Activating Token Index: 115

Text #1

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.6658. Min Act: -0.0000

Data Index: 1488966 (Python Code)

Max Activating Token Index: 849

Text #2

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.4443. Min Act: -0.0000

Data Index: 1656374 (Python Code)

Max Activating Token Index: 555

Text #3

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.4882. Min Act: -0.0000

Data Index: 1379654 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.2109. Min Act: -0.0000

Data Index: 1484301 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.2217. Min Act: -0.0000

Data Index: 1459658 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.4929. Min Act: -0.0000

Data Index: 1493717 (Python Code)

Max Activating Token Index: 807

Text #7

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.0981. Min Act: -0.0000

Data Index: 1554253 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.0935. Min Act: -0.0000

Data Index: 1399608 (Python Code)

Max Activating Token Index: 293

Text #9

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.0802. Min Act: -0.0000

Data Index: 1510675 (Python Code)

Max Activating Token Index: 851

Text #10

Max Range: 2.7229. Min Range: -2.7229

Max Act: 1.9411. Min Act: -0.0000

Data Index: 1510163 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.0246. Min Act: -0.0000

Data Index: 1469376 (Python Code)

Max Activating Token Index: 491

Text #12

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.0019. Min Act: -0.0000

Data Index: 1360473 (Python Code)

Max Activating Token Index: 702

Text #13

Max Range: 2.7229. Min Range: -2.7229

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1484051 (Python Code)

Max Activating Token Index: 310

Text #14

Max Range: 2.7229. Min Range: -2.7229

Max Act: 1.9712. Min Act: -0.0000

Data Index: 1382869 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 2.7229. Min Range: -2.7229

Max Act: 1.8454. Min Act: -0.0000

Data Index: 1517875 (Python Code)

Max Activating Token Index: 1000

Text #16

Max Range: 2.7229. Min Range: -2.7229

Max Act: 1.9524. Min Act: -0.0000

Data Index: 705777 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 2.7229. Min Range: -2.7229

Max Act: 1.9227. Min Act: -0.0000

Data Index: 1570926 (Python Code)

Max Activating Token Index: 946

Text #18

Max Range: 2.7229. Min Range: -2.7229

Max Act: 1.8117. Min Act: -0.0000

Data Index: 463316 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 2.7229. Min Range: -2.7229

Max Act: 2.1229. Min Act: -0.0000

Data Index: 1605829 (Python Code)

Max Activating Token Index: 195