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

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

Neuron 1713 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: 0.1230. Min Range: -0.1230

Max Act: 0.1181. Min Act: -0.0001

Data Index: 506051 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1208. Min Act: -0.0001

Data Index: 945961 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1081. Min Act: -0.0001

Data Index: 98957 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1230. Min Act: -0.0001

Data Index: 422645 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1081. Min Act: -0.0001

Data Index: 241035 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1050. Min Act: -0.0001

Data Index: 364542 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1090. Min Act: -0.0001

Data Index: 477394 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1054. Min Act: -0.0001

Data Index: 310551 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0998. Min Act: -0.0001

Data Index: 947537 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0954. Min Act: -0.0001

Data Index: 335095 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1179664 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1062661 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0973. Min Act: -0.0001

Data Index: 501567 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0963. Min Act: -0.0001

Data Index: 841279 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0951. Min Act: -0.0001

Data Index: 970078 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0908. Min Act: -0.0001

Data Index: 930646 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0947. Min Act: -0.0001

Data Index: 870893 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0910. Min Act: -0.0001

Data Index: 87797 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1006008 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0933. Min Act: -0.0001

Data Index: 30777 (C4 (Web Text))

Max Activating Token Index: 968