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

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

Neuron 937 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: 1.9842. Min Range: -1.9842

Max Act: 1.8825. Min Act: -0.0000

Data Index: 1305815 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.9842. Min Act: -0.0000

Data Index: 256548 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.8681. Min Act: -0.0000

Data Index: 612116 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.5256. Min Act: -0.0000

Data Index: 698497 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.5627. Min Act: -0.0000

Data Index: 934012 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.5470. Min Act: -0.0000

Data Index: 714172 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.5584. Min Act: -0.0000

Data Index: 1109879 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.5251. Min Act: -0.0000

Data Index: 344142 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1233192 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.3532. Min Act: -0.0000

Data Index: 734244 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1546252 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1276769 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1562216 (Python Code)

Max Activating Token Index: 541

Text #13

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.2779. Min Act: -0.0000

Data Index: 260619 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.3552. Min Act: -0.0000

Data Index: 990348 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1396207 (Python Code)

Max Activating Token Index: 963

Text #16

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.3077. Min Act: -0.0000

Data Index: 403887 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.3659. Min Act: -0.0000

Data Index: 771383 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.2787. Min Act: -0.0000

Data Index: 1511100 (Python Code)

Max Activating Token Index: 744

Text #19

Max Range: 1.9842. Min Range: -1.9842

Max Act: 1.2310. Min Act: -0.0000

Data Index: 1520460 (Python Code)

Max Activating Token Index: 671