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

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

Neuron 3570 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1345. Min Range: -7.1345

Max Act: 6.8873. Min Act: -0.0001

Data Index: 1553028 (Python Code)

Max Activating Token Index: 693

Text #1

Max Range: 7.1345. Min Range: -7.1345

Max Act: 6.9539. Min Act: -0.0001

Data Index: 1572330 (Python Code)

Max Activating Token Index: 175

Text #2

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.5397. Min Act: -0.0001

Data Index: 1635064 (Python Code)

Max Activating Token Index: 174

Text #3

Max Range: 7.1345. Min Range: -7.1345

Max Act: 7.1345. Min Act: -0.0001

Data Index: 1487997 (Python Code)

Max Activating Token Index: 225

Text #4

Max Range: 7.1345. Min Range: -7.1345

Max Act: 6.5114. Min Act: -0.0001

Data Index: 1525210 (Python Code)

Max Activating Token Index: 84

Text #5

Max Range: 7.1345. Min Range: -7.1345

Max Act: 6.3505. Min Act: -0.0001

Data Index: 1454023 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.8079. Min Act: -0.0001

Data Index: 1531248 (Python Code)

Max Activating Token Index: 245

Text #7

Max Range: 7.1345. Min Range: -7.1345

Max Act: 6.4590. Min Act: -0.0001

Data Index: 1447676 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.8620. Min Act: -0.0001

Data Index: 1528404 (Python Code)

Max Activating Token Index: 274

Text #9

Max Range: 7.1345. Min Range: -7.1345

Max Act: 6.0493. Min Act: -0.0001

Data Index: 1436570 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 7.1345. Min Range: -7.1345

Max Act: 6.4750. Min Act: -0.0001

Data Index: 1630966 (Python Code)

Max Activating Token Index: 600

Text #11

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.9583. Min Act: -0.0001

Data Index: 1552977 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.8607. Min Act: -0.0001

Data Index: 1474974 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.6791. Min Act: -0.0001

Data Index: 1607859 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 7.1345. Min Range: -7.1345

Max Act: 6.2338. Min Act: -0.0001

Data Index: 1425919 (Python Code)

Max Activating Token Index: 263

Text #15

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.8182. Min Act: -0.0001

Data Index: 1450759 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.9969. Min Act: -0.0001

Data Index: 1427491 (Python Code)

Max Activating Token Index: 738

Text #17

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.0753. Min Act: -0.0001

Data Index: 1464518 (Python Code)

Max Activating Token Index: 713

Text #18

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.5949. Min Act: -0.0001

Data Index: 1635391 (Python Code)

Max Activating Token Index: 104

Text #19

Max Range: 7.1345. Min Range: -7.1345

Max Act: 5.5995. Min Act: -0.0001

Data Index: 1393193 (Python Code)

Max Activating Token Index: 425