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

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

Neuron 2924 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8376. Min Act: -0.0001

Data Index: 1332297 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8582. Min Act: -0.0001

Data Index: 274468 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7892. Min Act: -0.0001

Data Index: 614652 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7868. Min Act: -0.0001

Data Index: 712653 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8309. Min Act: -0.0001

Data Index: 399361 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8035. Min Act: -0.0001

Data Index: 1070623 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7333. Min Act: -0.0001

Data Index: 805921 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7515. Min Act: -0.0001

Data Index: 1157160 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6970. Min Act: -0.0001

Data Index: 143295 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6942. Min Act: -0.0001

Data Index: 1225305 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6714. Min Act: -0.0001

Data Index: 1163052 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6114. Min Act: -0.0001

Data Index: 517592 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6842. Min Act: -0.0001

Data Index: 713742 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6675. Min Act: -0.0001

Data Index: 1335955 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6777. Min Act: -0.0001

Data Index: 81839 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6351. Min Act: -0.0001

Data Index: 537843 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6252. Min Act: -0.0001

Data Index: 105275 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6165. Min Act: -0.0001

Data Index: 606422 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.5961. Min Act: -0.0001

Data Index: 422216 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6561. Min Act: -0.0001

Data Index: 215251 (C4 (Web Text))

Max Activating Token Index: 299