Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3898 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.8926. Min Act: -0.0001

Data Index: 591847 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7884. Min Act: -0.0001

Data Index: 816503 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7777. Min Act: -0.0001

Data Index: 126106 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7792. Min Act: -0.0001

Data Index: 93800 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.8037. Min Act: -0.0001

Data Index: 942588 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7192. Min Act: -0.0001

Data Index: 414034 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7610. Min Act: -0.0001

Data Index: 454759 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7456. Min Act: -0.0001

Data Index: 1098846 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7426. Min Act: -0.0001

Data Index: 1194685 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7412. Min Act: -0.0001

Data Index: 617324 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7576. Min Act: -0.0001

Data Index: 48576 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7182. Min Act: -0.0001

Data Index: 632220 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7213. Min Act: -0.0001

Data Index: 1312577 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.6832. Min Act: -0.0001

Data Index: 653577 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7024. Min Act: -0.0001

Data Index: 372042 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.6489. Min Act: -0.0001

Data Index: 1025700 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.7115. Min Act: -0.0001

Data Index: 1286906 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.6787. Min Act: -0.0001

Data Index: 651552 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.6508. Min Act: -0.0001

Data Index: 400529 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.8926. Min Range: -0.8926

Max Act: 0.6981. Min Act: -0.0001

Data Index: 1195037 (C4 (Web Text))

Max Activating Token Index: 839