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

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

Neuron 3554 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.2968. Min Range: -10.2968

Max Act: 10.2267. Min Act: -0.0000

Data Index: 1539378 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 10.2968. Min Range: -10.2968

Max Act: 10.2968. Min Act: -0.0000

Data Index: 1526730 (Python Code)

Max Activating Token Index: 60

Text #2

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.9519. Min Act: -0.0000

Data Index: 1435083 (Python Code)

Max Activating Token Index: 547

Text #3

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.3856. Min Act: -0.0000

Data Index: 1362786 (Python Code)

Max Activating Token Index: 129

Text #4

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.5587. Min Act: -0.0000

Data Index: 1491597 (Python Code)

Max Activating Token Index: 477

Text #5

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.6496. Min Act: -0.0000

Data Index: 1431157 (Python Code)

Max Activating Token Index: 50

Text #6

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.3797. Min Act: -0.0000

Data Index: 1402607 (Python Code)

Max Activating Token Index: 1015

Text #7

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.4696. Min Act: -0.0000

Data Index: 1636859 (Python Code)

Max Activating Token Index: 983

Text #8

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.2937. Min Act: -0.0000

Data Index: 1523332 (Python Code)

Max Activating Token Index: 586

Text #9

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.0926. Min Act: -0.0000

Data Index: 1454841 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.4978. Min Act: -0.0000

Data Index: 1641546 (Python Code)

Max Activating Token Index: 871

Text #11

Max Range: 10.2968. Min Range: -10.2968

Max Act: 8.9912. Min Act: -0.0000

Data Index: 1558402 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.2857. Min Act: -0.0000

Data Index: 1387457 (Python Code)

Max Activating Token Index: 876

Text #13

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.1216. Min Act: -0.0000

Data Index: 1379368 (Python Code)

Max Activating Token Index: 612

Text #14

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.2790. Min Act: -0.0000

Data Index: 1386028 (Python Code)

Max Activating Token Index: 950

Text #15

Max Range: 10.2968. Min Range: -10.2968

Max Act: 8.9409. Min Act: -0.0000

Data Index: 1543886 (Python Code)

Max Activating Token Index: 516

Text #16

Max Range: 10.2968. Min Range: -10.2968

Max Act: 8.7761. Min Act: -0.0000

Data Index: 1576625 (Python Code)

Max Activating Token Index: 587

Text #17

Max Range: 10.2968. Min Range: -10.2968

Max Act: 9.0733. Min Act: -0.0000

Data Index: 1633206 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 10.2968. Min Range: -10.2968

Max Act: 8.8189. Min Act: -0.0000

Data Index: 1498954 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 10.2968. Min Range: -10.2968

Max Act: 8.8021. Min Act: -0.0000

Data Index: 1656886 (Python Code)

Max Activating Token Index: 584