Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5980 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.6268. Min Act: -0.0001

Data Index: 374387 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5337. Min Act: -0.0001

Data Index: 743263 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4975. Min Act: -0.0001

Data Index: 1309987 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4439. Min Act: -0.0001

Data Index: 996975 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4424. Min Act: -0.0001

Data Index: 836047 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4082. Min Act: -0.0001

Data Index: 130852 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3810. Min Act: -0.0001

Data Index: 983678 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3523. Min Act: -0.0001

Data Index: 1076318 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3742. Min Act: -0.0001

Data Index: 122580 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3476. Min Act: -0.0001

Data Index: 991260 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3741. Min Act: -0.0001

Data Index: 45493 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3477. Min Act: -0.0001

Data Index: 796881 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3545. Min Act: -0.0001

Data Index: 789502 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3458. Min Act: -0.0001

Data Index: 763393 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3449. Min Act: -0.0001

Data Index: 1102752 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3274. Min Act: -0.0000

Data Index: 220523 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.2997. Min Act: -0.0001

Data Index: 866526 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.2861. Min Act: -0.0001

Data Index: 1095505 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.2883. Min Act: -0.0001

Data Index: 930936 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.2854. Min Act: -0.0001

Data Index: 1098508 (C4 (Web Text))

Max Activating Token Index: 25