Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 902 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0525. Min Range: -1.0525

Max Act: 1.0525. Min Act: -0.0001

Data Index: 1598684 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.8936. Min Act: -0.0001

Data Index: 1447461 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.8096. Min Act: -0.0001

Data Index: 1364458 (Python Code)

Max Activating Token Index: 577

Text #3

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.8342. Min Act: -0.0001

Data Index: 1469752 (Python Code)

Max Activating Token Index: 574

Text #4

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7920. Min Act: -0.0001

Data Index: 1616631 (Python Code)

Max Activating Token Index: 779

Text #5

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7788. Min Act: -0.0001

Data Index: 1428362 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.8202. Min Act: -0.0001

Data Index: 1383730 (Python Code)

Max Activating Token Index: 716

Text #7

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7956. Min Act: -0.0001

Data Index: 1460021 (Python Code)

Max Activating Token Index: 983

Text #8

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7944. Min Act: -0.0001

Data Index: 1424186 (Python Code)

Max Activating Token Index: 440

Text #9

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.8137. Min Act: -0.0001

Data Index: 1656213 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7443. Min Act: -0.0001

Data Index: 1386976 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7649. Min Act: -0.0001

Data Index: 1612567 (Python Code)

Max Activating Token Index: 745

Text #12

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7535. Min Act: -0.0001

Data Index: 1442062 (Python Code)

Max Activating Token Index: 389

Text #13

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7525. Min Act: -0.0001

Data Index: 1604453 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7742. Min Act: -0.0001

Data Index: 1382526 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7708. Min Act: -0.0001

Data Index: 1648376 (Python Code)

Max Activating Token Index: 799

Text #16

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7742. Min Act: -0.0001

Data Index: 1413632 (Python Code)

Max Activating Token Index: 830

Text #17

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7960. Min Act: -0.0001

Data Index: 1638625 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7177. Min Act: -0.0001

Data Index: 1645763 (Python Code)

Max Activating Token Index: 500

Text #19

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7392. Min Act: -0.0001

Data Index: 1574339 (Python Code)

Max Activating Token Index: 149