Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1025 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3732. Min Act: -0.0001

Data Index: 1121142 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3509. Min Act: -0.0001

Data Index: 143214 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2975. Min Act: -0.0001

Data Index: 1446925 (Python Code)

Max Activating Token Index: 671

Text #3

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3308. Min Act: -0.0001

Data Index: 691490 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3364. Min Act: -0.0001

Data Index: 1399017 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3318. Min Act: -0.0001

Data Index: 1546724 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3051. Min Act: -0.0001

Data Index: 531902 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3128. Min Act: -0.0001

Data Index: 1588363 (Python Code)

Max Activating Token Index: 498

Text #8

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3012. Min Act: -0.0001

Data Index: 1425113 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2886. Min Act: -0.0001

Data Index: 819510 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1456395 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2944. Min Act: -0.0001

Data Index: 1364706 (Python Code)

Max Activating Token Index: 275

Text #12

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1096171 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2844. Min Act: -0.0001

Data Index: 1483693 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2987. Min Act: -0.0001

Data Index: 1568183 (Python Code)

Max Activating Token Index: 205

Text #15

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2593. Min Act: -0.0001

Data Index: 129040 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2952. Min Act: -0.0001

Data Index: 1640816 (Python Code)

Max Activating Token Index: 92

Text #17

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1300417 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1468949 (Python Code)

Max Activating Token Index: 218

Text #19

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1362705 (Python Code)

Max Activating Token Index: 867