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

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

Neuron 2592 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: 0.9482. Min Range: -0.9482

Max Act: 0.9482. Min Act: -0.0001

Data Index: 818490 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8754. Min Act: -0.0001

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7444. Min Act: -0.0001

Data Index: 818437 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8345. Min Act: -0.0001

Data Index: 850438 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7066. Min Act: -0.0001

Data Index: 973700 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7222. Min Act: -0.0000

Data Index: 83908 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8934. Min Act: -0.0001

Data Index: 317800 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7634. Min Act: -0.0001

Data Index: 266741 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7489. Min Act: -0.0001

Data Index: 518353 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7722. Min Act: -0.0001

Data Index: 1063843 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8143. Min Act: -0.0001

Data Index: 367770 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1156761 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8003. Min Act: -0.0000

Data Index: 980979 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7732. Min Act: -0.0001

Data Index: 970328 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7484. Min Act: -0.0001

Data Index: 700836 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.6790. Min Act: -0.0001

Data Index: 1116784 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7125. Min Act: -0.0001

Data Index: 535547 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7508. Min Act: -0.0001

Data Index: 27288 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.5946. Min Act: -0.0001

Data Index: 1007190 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7328. Min Act: -0.0001

Data Index: 1197520 (C4 (Web Text))

Max Activating Token Index: 237