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

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

Neuron 535 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: 0.2053. Min Range: -0.2053

Max Act: 0.2053. Min Act: -0.0000

Data Index: 744629 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1682. Min Act: -0.0000

Data Index: 384754 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1374154 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1300748 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1132261 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1384. Min Act: -0.0000

Data Index: 676079 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1470130 (Python Code)

Max Activating Token Index: 141

Text #7

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1388737 (Python Code)

Max Activating Token Index: 54

Text #8

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1560430 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1362. Min Act: -0.0000

Data Index: 167682 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1484197 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1462971 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1512415 (Python Code)

Max Activating Token Index: 118

Text #13

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1299. Min Act: -0.0000

Data Index: 738854 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1591621 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1424808 (Python Code)

Max Activating Token Index: 107

Text #16

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1649117 (Python Code)

Max Activating Token Index: 209

Text #17

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1590705 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1540183 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1534586 (Python Code)

Max Activating Token Index: 98