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

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

Neuron 5396 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.5657. Min Act: -0.0002

Data Index: 652863 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.5121. Min Act: -0.0002

Data Index: 375265 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4950. Min Act: -0.0002

Data Index: 1337041 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4684. Min Act: -0.0002

Data Index: 421645 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4680. Min Act: -0.0003

Data Index: 166827 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4544. Min Act: -0.0002

Data Index: 1232662 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4438. Min Act: -0.0002

Data Index: 1104159 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4509. Min Act: -0.0002

Data Index: 929396 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4257. Min Act: -0.0002

Data Index: 1184724 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4083. Min Act: -0.0002

Data Index: 784998 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4150. Min Act: -0.0002

Data Index: 874727 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3998. Min Act: -0.0002

Data Index: 145699 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4025. Min Act: -0.0002

Data Index: 183040 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3935. Min Act: -0.0002

Data Index: 92491 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4022. Min Act: -0.0003

Data Index: 1098261 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3950. Min Act: -0.0002

Data Index: 376000 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3968. Min Act: -0.0002

Data Index: 1043301 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3961. Min Act: -0.0002

Data Index: 1027144 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3911. Min Act: -0.0002

Data Index: 381089 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3835. Min Act: -0.0003

Data Index: 978722 (C4 (Web Text))

Max Activating Token Index: 877