Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2644 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.7099. Min Act: -0.0000

Data Index: 382267 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5592. Min Act: -0.0000

Data Index: 530656 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1216299 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5355. Min Act: -0.0000

Data Index: 495508 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4792. Min Act: -0.0000

Data Index: 813036 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4815. Min Act: -0.0000

Data Index: 779594 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4848. Min Act: -0.0000

Data Index: 415789 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4538. Min Act: -0.0000

Data Index: 107673 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1085921 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4585. Min Act: -0.0000

Data Index: 309899 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4330. Min Act: -0.0000

Data Index: 64176 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1240770 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4436. Min Act: -0.0000

Data Index: 413762 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4464. Min Act: -0.0000

Data Index: 35714 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4139. Min Act: -0.0000

Data Index: 393102 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.3925. Min Act: -0.0000

Data Index: 846506 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1148842 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4024. Min Act: -0.0000

Data Index: 954568 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.3860. Min Act: -0.0000

Data Index: 894493 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4285. Min Act: -0.0000

Data Index: 527542 (C4 (Web Text))

Max Activating Token Index: 542