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

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

Neuron 2312 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: 0.4953. Min Range: -0.4953

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1182040 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4550. Min Act: -0.0000

Data Index: 38625 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4953. Min Act: -0.0000

Data Index: 440378 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4894. Min Act: -0.0000

Data Index: 697683 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1265058 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4567. Min Act: -0.0000

Data Index: 746849 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4230. Min Act: -0.0000

Data Index: 55932 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1127229 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3982. Min Act: -0.0000

Data Index: 681903 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4018. Min Act: -0.0000

Data Index: 912281 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3863. Min Act: -0.0000

Data Index: 925133 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3909. Min Act: -0.0000

Data Index: 444702 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3830. Min Act: -0.0000

Data Index: 895145 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3708. Min Act: -0.0000

Data Index: 929000 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3026. Min Act: -0.0000

Data Index: 429118 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3632. Min Act: -0.0000

Data Index: 22771 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3689. Min Act: -0.0000

Data Index: 302608 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.2987. Min Act: -0.0000

Data Index: 589139 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3476. Min Act: -0.0000

Data Index: 140874 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1098904 (C4 (Web Text))

Max Activating Token Index: 730