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

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

Neuron 3028 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3575. Min Act: -0.0000

Data Index: 176088 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1353798 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3017. Min Act: -0.0000

Data Index: 543229 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3101. Min Act: -0.0000

Data Index: 908237 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3296. Min Act: -0.0000

Data Index: 831196 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3433. Min Act: -0.0000

Data Index: 410084 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3170. Min Act: -0.0000

Data Index: 460044 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3125. Min Act: -0.0000

Data Index: 933784 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3198. Min Act: -0.0000

Data Index: 559098 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3081. Min Act: -0.0000

Data Index: 624726 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3174. Min Act: -0.0000

Data Index: 383902 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2992. Min Act: -0.0000

Data Index: 188774 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2961. Min Act: -0.0000

Data Index: 815844 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2761. Min Act: -0.0000

Data Index: 122981 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2922. Min Act: -0.0000

Data Index: 19637 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2908. Min Act: -0.0000

Data Index: 35546 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2799. Min Act: -0.0000

Data Index: 803957 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2679. Min Act: -0.0000

Data Index: 62132 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2690. Min Act: -0.0000

Data Index: 912169 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2870. Min Act: -0.0000

Data Index: 403052 (C4 (Web Text))

Max Activating Token Index: 648