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

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

Neuron 984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2552. Min Range: -1.2552

Max Act: 1.2552. Min Act: -0.0001

Data Index: 14815 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.2552. Min Range: -1.2552

Max Act: 1.2128. Min Act: -0.0001

Data Index: 573774 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 1.2552. Min Range: -1.2552

Max Act: 1.1854. Min Act: -0.0001

Data Index: 1190337 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 1.2552. Min Range: -1.2552

Max Act: 1.0977. Min Act: -0.0001

Data Index: 280733 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 1.2552. Min Range: -1.2552

Max Act: 1.0657. Min Act: -0.0001

Data Index: 584127 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9608. Min Act: -0.0001

Data Index: 1217431 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9611. Min Act: -0.0001

Data Index: 713148 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9520. Min Act: -0.0001

Data Index: 303065 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9655. Min Act: -0.0000

Data Index: 205832 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 1.2552. Min Range: -1.2552

Max Act: 1.0043. Min Act: -0.0001

Data Index: 142635 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.2552. Min Range: -1.2552

Max Act: 1.0224. Min Act: -0.0001

Data Index: 120244 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9085. Min Act: -0.0000

Data Index: 389704 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9288. Min Act: -0.0001

Data Index: 644623 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1277512 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9156. Min Act: -0.0001

Data Index: 32206 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9321. Min Act: -0.0001

Data Index: 840554 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.8769. Min Act: -0.0000

Data Index: 908919 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9947. Min Act: -0.0000

Data Index: 689048 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.8009. Min Act: -0.0001

Data Index: 1251512 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.8965. Min Act: -0.0001

Data Index: 25839 (C4 (Web Text))

Max Activating Token Index: 362