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

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

Neuron 1308 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.5004. Min Act: -0.0000

Data Index: 410208 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4449. Min Act: -0.0001

Data Index: 270552 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4448. Min Act: -0.0000

Data Index: 341247 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4016. Min Act: -0.0001

Data Index: 406673 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3954. Min Act: -0.0001

Data Index: 197014 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3776. Min Act: -0.0001

Data Index: 486223 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3695. Min Act: -0.0000

Data Index: 539116 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3629. Min Act: -0.0001

Data Index: 625186 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3543. Min Act: -0.0000

Data Index: 17011 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3232. Min Act: -0.0001

Data Index: 86720 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3305. Min Act: -0.0001

Data Index: 519286 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3390. Min Act: -0.0001

Data Index: 674790 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3005. Min Act: -0.0001

Data Index: 803939 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3068. Min Act: -0.0001

Data Index: 497562 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3280. Min Act: -0.0001

Data Index: 251524 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3371. Min Act: -0.0001

Data Index: 1146957 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3050. Min Act: -0.0001

Data Index: 1249867 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3108. Min Act: -0.0001

Data Index: 1083345 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2908. Min Act: -0.0001

Data Index: 407145 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2960. Min Act: -0.0001

Data Index: 192208 (C4 (Web Text))

Max Activating Token Index: 507