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

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

Neuron 1283 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: 2.4523. Min Range: -2.4523

Max Act: 2.4523. Min Act: -0.0000

Data Index: 1213078 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.2316. Min Act: -0.0000

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.2842. Min Act: -0.0000

Data Index: 841886 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.0989. Min Act: -0.0000

Data Index: 1590788 (Python Code)

Max Activating Token Index: 517

Text #4

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.0721. Min Act: -0.0000

Data Index: 1643992 (Python Code)

Max Activating Token Index: 834

Text #5

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.0259. Min Act: -0.0000

Data Index: 1399100 (Python Code)

Max Activating Token Index: 876

Text #6

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8859. Min Act: -0.0000

Data Index: 960348 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.9792. Min Act: -0.0000

Data Index: 245912 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8335. Min Act: -0.0000

Data Index: 32949 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.0182. Min Act: -0.0000

Data Index: 1386351 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.9918. Min Act: -0.0000

Data Index: 187051 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8099. Min Act: -0.0000

Data Index: 1151554 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8716. Min Act: -0.0000

Data Index: 1468886 (Python Code)

Max Activating Token Index: 865

Text #13

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.7295. Min Act: -0.0000

Data Index: 1445050 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.7149. Min Act: -0.0000

Data Index: 1397180 (Python Code)

Max Activating Token Index: 971

Text #15

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.7185. Min Act: -0.0000

Data Index: 179652 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.9036. Min Act: -0.0000

Data Index: 1588832 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8920. Min Act: -0.0000

Data Index: 1410092 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.7129. Min Act: -0.0000

Data Index: 741565 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.7699. Min Act: -0.0000

Data Index: 1103431 (C4 (Web Text))

Max Activating Token Index: 681