Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1682 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5176. Min Act: -0.0000

Data Index: 362825 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4382. Min Act: -0.0001

Data Index: 357717 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4178. Min Act: -0.0001

Data Index: 930124 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3952. Min Act: -0.0000

Data Index: 821750 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3980. Min Act: -0.0000

Data Index: 811676 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1251976 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3782. Min Act: -0.0000

Data Index: 464086 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3550. Min Act: -0.0000

Data Index: 107410 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3538. Min Act: -0.0001

Data Index: 991625 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1024604 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3734. Min Act: -0.0000

Data Index: 474123 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3560. Min Act: -0.0001

Data Index: 993778 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3555. Min Act: -0.0001

Data Index: 693698 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3354. Min Act: -0.0000

Data Index: 17796 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3538. Min Act: -0.0000

Data Index: 5914 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3544. Min Act: -0.0000

Data Index: 513282 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3613. Min Act: -0.0001

Data Index: 395083 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.2935. Min Act: -0.0000

Data Index: 340472 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1189924 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3443. Min Act: -0.0001

Data Index: 4956 (C4 (Web Text))

Max Activating Token Index: 121