Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 546 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8742. Min Act: -0.0001

Data Index: 476784 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8821. Min Act: -0.0001

Data Index: 204504 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8665. Min Act: -0.0001

Data Index: 430603 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8419. Min Act: -0.0001

Data Index: 806541 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8140. Min Act: -0.0001

Data Index: 478684 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8382. Min Act: -0.0001

Data Index: 47357 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7988. Min Act: -0.0001

Data Index: 48410 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7479. Min Act: -0.0001

Data Index: 907887 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7943. Min Act: -0.0001

Data Index: 366517 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7272. Min Act: -0.0001

Data Index: 343233 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7238. Min Act: -0.0001

Data Index: 318625 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7171. Min Act: -0.0001

Data Index: 1139566 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6910. Min Act: -0.0001

Data Index: 966871 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6893. Min Act: -0.0001

Data Index: 989314 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6999. Min Act: -0.0001

Data Index: 88954 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6921. Min Act: -0.0001

Data Index: 1211086 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6238. Min Act: -0.0001

Data Index: 293350 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6394. Min Act: -0.0001

Data Index: 1324187 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6780. Min Act: -0.0001

Data Index: 569279 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6378. Min Act: -0.0001

Data Index: 810022 (C4 (Web Text))

Max Activating Token Index: 295