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

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

Neuron 814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.4091. Min Act: -0.0000

Data Index: 1176864 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.4003. Min Act: -0.0000

Data Index: 1276878 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.2575. Min Act: -0.0000

Data Index: 1203183 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.3806. Min Act: -0.0000

Data Index: 1294838 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.2499. Min Act: -0.0000

Data Index: 817950 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.2633. Min Act: -0.0000

Data Index: 683147 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.3851. Min Act: -0.0000

Data Index: 1299600 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.3937. Min Act: -0.0000

Data Index: 973675 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.2337. Min Act: -0.0000

Data Index: 133301 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.3655. Min Act: -0.0000

Data Index: 823944 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.3845. Min Act: -0.0000

Data Index: 419876 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.3687. Min Act: -0.0000

Data Index: 257604 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.3731. Min Act: -0.0000

Data Index: 525178 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.3540. Min Act: -0.0000

Data Index: 590521 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.3561. Min Act: -0.0000

Data Index: 191817 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.2304. Min Act: -0.0000

Data Index: 440625 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.4473. Min Act: -0.0000

Data Index: 1303153 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.2146. Min Act: -0.0000

Data Index: 48148 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.2976. Min Act: -0.0000

Data Index: 866607 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 2.4473. Min Range: -2.4473

Max Act: 2.2942. Min Act: -0.0000

Data Index: 1295941 (C4 (Web Text))

Max Activating Token Index: 359