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

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

Neuron 4281 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.8634. Min Act: -0.0001

Data Index: 1534303 (Python Code)

Max Activating Token Index: 949

Text #1

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.9113. Min Act: -0.0000

Data Index: 223170 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7661. Min Act: -0.0001

Data Index: 1469359 (Python Code)

Max Activating Token Index: 289

Text #3

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.8234. Min Act: -0.0001

Data Index: 1437412 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1419360 (Python Code)

Max Activating Token Index: 413

Text #5

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7335. Min Act: -0.0001

Data Index: 1530532 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1531125 (Python Code)

Max Activating Token Index: 112

Text #7

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1388176 (Python Code)

Max Activating Token Index: 935

Text #8

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6879. Min Act: -0.0001

Data Index: 1422007 (Python Code)

Max Activating Token Index: 448

Text #9

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7107. Min Act: -0.0001

Data Index: 1476717 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7361. Min Act: -0.0001

Data Index: 1471626 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6300. Min Act: -0.0001

Data Index: 1503374 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6345. Min Act: -0.0001

Data Index: 1551468 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6256. Min Act: -0.0001

Data Index: 1590982 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1076469 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6068. Min Act: -0.0001

Data Index: 1378963 (Python Code)

Max Activating Token Index: 1016

Text #16

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.5998. Min Act: -0.0001

Data Index: 1512908 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.5866. Min Act: -0.0001

Data Index: 1642836 (Python Code)

Max Activating Token Index: 156

Text #18

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.5973. Min Act: -0.0001

Data Index: 1554987 (Python Code)

Max Activating Token Index: 662

Text #19

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1586366 (Python Code)

Max Activating Token Index: 446