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

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

Neuron 870 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.8995. Min Act: -0.0000

Data Index: 645208 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1364556 (Python Code)

Max Activating Token Index: 96

Text #2

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.6391. Min Act: -0.0000

Data Index: 1493906 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.7208. Min Act: -0.0000

Data Index: 1595223 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.6368. Min Act: -0.0000

Data Index: 1649214 (Python Code)

Max Activating Token Index: 48

Text #5

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.5986. Min Act: -0.0000

Data Index: 1656913 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.4861. Min Act: -0.0000

Data Index: 1530381 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1498082 (Python Code)

Max Activating Token Index: 104

Text #8

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1261505 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1387545 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1362972 (Python Code)

Max Activating Token Index: 326

Text #11

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.2790. Min Act: -0.0000

Data Index: 1487604 (Python Code)

Max Activating Token Index: 369

Text #12

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.2950. Min Act: -0.0000

Data Index: 278581 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.4169. Min Act: -0.0000

Data Index: 1611103 (Python Code)

Max Activating Token Index: 147

Text #14

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.4020. Min Act: -0.0000

Data Index: 460115 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.3261. Min Act: -0.0000

Data Index: 1375931 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.3112. Min Act: -0.0000

Data Index: 1467790 (Python Code)

Max Activating Token Index: 736

Text #17

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.3427. Min Act: -0.0000

Data Index: 1440880 (Python Code)

Max Activating Token Index: 108

Text #18

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.4818. Min Act: -0.0000

Data Index: 1590417 (Python Code)

Max Activating Token Index: 326

Text #19

Max Range: 1.8995. Min Range: -1.8995

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1599808 (Python Code)

Max Activating Token Index: 368