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

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

Neuron 4920 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: 0.5362. Min Range: -0.5362

Max Act: 0.5362. Min Act: -0.0000

Data Index: 518793 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4880. Min Act: -0.0000

Data Index: 132705 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4862. Min Act: -0.0000

Data Index: 671096 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1248904 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4598. Min Act: -0.0000

Data Index: 507367 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4628. Min Act: -0.0000

Data Index: 238923 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1225512 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4650. Min Act: -0.0000

Data Index: 231013 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4502. Min Act: -0.0000

Data Index: 17114 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5155. Min Act: -0.0000

Data Index: 193297 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4337. Min Act: -0.0000

Data Index: 482009 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4557. Min Act: -0.0000

Data Index: 624819 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4302. Min Act: -0.0000

Data Index: 621634 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4283. Min Act: -0.0000

Data Index: 425889 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1071064 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4097. Min Act: -0.0000

Data Index: 378966 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1278365 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4058. Min Act: -0.0000

Data Index: 719729 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3802. Min Act: -0.0000

Data Index: 998995 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4033. Min Act: -0.0000

Data Index: 76312 (C4 (Web Text))

Max Activating Token Index: 1010