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

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

Neuron 286 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3375. Min Act: -0.0001

Data Index: 1459672 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3297. Min Act: -0.0001

Data Index: 1534615 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3107. Min Act: -0.0001

Data Index: 1412955 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3078. Min Act: -0.0001

Data Index: 1421959 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3176. Min Act: -0.0001

Data Index: 1512001 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1601631 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3019. Min Act: -0.0001

Data Index: 1520502 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1377529 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2935. Min Act: -0.0001

Data Index: 1599498 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2881. Min Act: -0.0001

Data Index: 1429766 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2908. Min Act: -0.0001

Data Index: 1513656 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2923. Min Act: -0.0001

Data Index: 1395716 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2990. Min Act: -0.0001

Data Index: 1566217 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2992. Min Act: -0.0001

Data Index: 1428920 (Python Code)

Max Activating Token Index: 43

Text #14

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2888. Min Act: -0.0001

Data Index: 1473664 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2887. Min Act: -0.0001

Data Index: 1498881 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2956. Min Act: -0.0001

Data Index: 1558024 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1559600 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2850. Min Act: -0.0001

Data Index: 1441280 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2847. Min Act: -0.0001

Data Index: 1464701 (Python Code)

Max Activating Token Index: 13