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

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

Neuron 3360 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8643. Min Range: -2.8643

Max Act: 2.8643. Min Act: -0.0000

Data Index: 1410153 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 2.8643. Min Range: -2.8643

Max Act: 2.3607. Min Act: -0.0000

Data Index: 1019088 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 2.8643. Min Range: -2.8643

Max Act: 2.2929. Min Act: -0.0000

Data Index: 369224 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 2.8643. Min Range: -2.8643

Max Act: 2.1707. Min Act: -0.0000

Data Index: 1488415 (Python Code)

Max Activating Token Index: 147

Text #4

Max Range: 2.8643. Min Range: -2.8643

Max Act: 2.1146. Min Act: -0.0000

Data Index: 1015079 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 2.8643. Min Range: -2.8643

Max Act: 2.2183. Min Act: -0.0000

Data Index: 1451210 (Python Code)

Max Activating Token Index: 371

Text #6

Max Range: 2.8643. Min Range: -2.8643

Max Act: 2.2247. Min Act: -0.0000

Data Index: 439622 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 2.8643. Min Range: -2.8643

Max Act: 2.0850. Min Act: -0.0000

Data Index: 1535849 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 2.8643. Min Range: -2.8643

Max Act: 2.0918. Min Act: -0.0000

Data Index: 585744 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 2.8643. Min Range: -2.8643

Max Act: 2.0889. Min Act: -0.0000

Data Index: 1609678 (Python Code)

Max Activating Token Index: 371

Text #10

Max Range: 2.8643. Min Range: -2.8643

Max Act: 1.9675. Min Act: -0.0000

Data Index: 1026871 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 2.8643. Min Range: -2.8643

Max Act: 1.8522. Min Act: -0.0000

Data Index: 136752 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 2.8643. Min Range: -2.8643

Max Act: 1.7746. Min Act: -0.0000

Data Index: 425339 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 2.8643. Min Range: -2.8643

Max Act: 1.8070. Min Act: -0.0000

Data Index: 570282 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 2.8643. Min Range: -2.8643

Max Act: 1.8807. Min Act: -0.0000

Data Index: 1138043 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 2.8643. Min Range: -2.8643

Max Act: 1.7606. Min Act: -0.0000

Data Index: 1323374 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 2.8643. Min Range: -2.8643

Max Act: 1.8264. Min Act: -0.0000

Data Index: 1021400 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 2.8643. Min Range: -2.8643

Max Act: 1.5211. Min Act: -0.0000

Data Index: 525742 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 2.8643. Min Range: -2.8643

Max Act: 1.6973. Min Act: -0.0000

Data Index: 725181 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 2.8643. Min Range: -2.8643

Max Act: 1.6774. Min Act: -0.0000

Data Index: 112168 (C4 (Web Text))

Max Activating Token Index: 418