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

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

Neuron 1447 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3742. Min Act: -0.0000

Data Index: 410966 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3507. Min Act: -0.0000

Data Index: 117213 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3540. Min Act: -0.0000

Data Index: 524009 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3487. Min Act: -0.0001

Data Index: 18673 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3517. Min Act: -0.0001

Data Index: 218746 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1107920 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3224. Min Act: -0.0001

Data Index: 1319077 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3060. Min Act: 0.0000

Data Index: 24815 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3018. Min Act: -0.0000

Data Index: 520944 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2875. Min Act: -0.0001

Data Index: 535052 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3089. Min Act: -0.0000

Data Index: 718979 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2916. Min Act: -0.0000

Data Index: 407935 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2921. Min Act: -0.0001

Data Index: 304215 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2818. Min Act: -0.0000

Data Index: 256928 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2814. Min Act: -0.0000

Data Index: 737110 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2880. Min Act: -0.0001

Data Index: 834335 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2836. Min Act: -0.0000

Data Index: 157040 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2691. Min Act: -0.0001

Data Index: 741672 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2690. Min Act: -0.0000

Data Index: 533263 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2666. Min Act: -0.0000

Data Index: 67850 (C4 (Web Text))

Max Activating Token Index: 543