Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 465 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.4004. Min Act: -0.0001

Data Index: 1222905 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3352. Min Act: -0.0001

Data Index: 802897 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3280. Min Act: -0.0001

Data Index: 173280 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3147. Min Act: -0.0001

Data Index: 917535 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3218. Min Act: -0.0001

Data Index: 1209193 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3371. Min Act: -0.0001

Data Index: 537032 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3171. Min Act: -0.0001

Data Index: 806129 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2543. Min Act: -0.0001

Data Index: 308493 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3071. Min Act: -0.0001

Data Index: 145065 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3016. Min Act: -0.0001

Data Index: 794182 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3129. Min Act: -0.0001

Data Index: 649202 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2877. Min Act: -0.0001

Data Index: 1336794 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2976. Min Act: -0.0001

Data Index: 316357 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2871. Min Act: -0.0001

Data Index: 117927 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2815. Min Act: -0.0001

Data Index: 321700 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2824. Min Act: -0.0001

Data Index: 142010 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2721. Min Act: -0.0001

Data Index: 830381 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2729. Min Act: -0.0001

Data Index: 618649 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2804. Min Act: -0.0001

Data Index: 1175790 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2601. Min Act: -0.0001

Data Index: 202019 (C4 (Web Text))

Max Activating Token Index: 1001