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

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

Neuron 902 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7615. Min Act: -0.0001

Data Index: 1614447 (Python Code)

Max Activating Token Index: 393

Text #1

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7933. Min Act: -0.0001

Data Index: 1613467 (Python Code)

Max Activating Token Index: 225

Text #2

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7492. Min Act: -0.0001

Data Index: 1386932 (Python Code)

Max Activating Token Index: 317

Text #3

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7162. Min Act: -0.0001

Data Index: 1606762 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7055. Min Act: -0.0001

Data Index: 1478422 (Python Code)

Max Activating Token Index: 267

Text #5

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6946. Min Act: -0.0001

Data Index: 1424245 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7042. Min Act: -0.0001

Data Index: 1647386 (Python Code)

Max Activating Token Index: 666

Text #7

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7318. Min Act: -0.0001

Data Index: 1501027 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6997. Min Act: -0.0001

Data Index: 1407412 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6320. Min Act: -0.0001

Data Index: 1650599 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6325. Min Act: -0.0001

Data Index: 1504129 (Python Code)

Max Activating Token Index: 912

Text #11

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6613. Min Act: -0.0001

Data Index: 1534522 (Python Code)

Max Activating Token Index: 546

Text #12

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6499. Min Act: -0.0001

Data Index: 1586243 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6476. Min Act: -0.0001

Data Index: 1362351 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6450. Min Act: -0.0001

Data Index: 1439083 (Python Code)

Max Activating Token Index: 532

Text #15

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6605. Min Act: -0.0001

Data Index: 1548328 (Python Code)

Max Activating Token Index: 823

Text #16

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6649. Min Act: -0.0001

Data Index: 1567705 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6639. Min Act: -0.0001

Data Index: 1424201 (Python Code)

Max Activating Token Index: 947

Text #18

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6642. Min Act: -0.0001

Data Index: 1559644 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6642. Min Act: -0.0001

Data Index: 1445009 (Python Code)

Max Activating Token Index: 3