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

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

Neuron 143 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0610. Min Range: -2.0610

Max Act: 2.0610. Min Act: -0.0001

Data Index: 131962 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.7988. Min Act: -0.0000

Data Index: 271148 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.6936. Min Act: -0.0000

Data Index: 331024 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.6057. Min Act: -0.0000

Data Index: 1308394 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.5485. Min Act: -0.0001

Data Index: 615389 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.5913. Min Act: -0.0001

Data Index: 1317031 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.5142. Min Act: -0.0000

Data Index: 747575 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4879. Min Act: -0.0001

Data Index: 35391 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4299. Min Act: -0.0001

Data Index: 111897 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4702. Min Act: -0.0001

Data Index: 793751 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.5045. Min Act: -0.0000

Data Index: 1354448 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4596. Min Act: -0.0001

Data Index: 826341 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4009. Min Act: -0.0001

Data Index: 1191549 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4160. Min Act: -0.0000

Data Index: 328329 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4119. Min Act: -0.0000

Data Index: 275792 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4417. Min Act: -0.0000

Data Index: 1060610 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4044. Min Act: -0.0000

Data Index: 60552 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4492. Min Act: -0.0000

Data Index: 1178357 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.3745. Min Act: -0.0000

Data Index: 942935 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.3583. Min Act: -0.0000

Data Index: 40487 (C4 (Web Text))

Max Activating Token Index: 88