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

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

Neuron 2320 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5313. Min Act: -0.0001

Data Index: 3501 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5655. Min Act: -0.0001

Data Index: 1392455 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1074029 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1136310 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5045. Min Act: -0.0001

Data Index: 1349414 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4741. Min Act: -0.0001

Data Index: 1230125 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4753. Min Act: -0.0001

Data Index: 1196539 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4450. Min Act: -0.0001

Data Index: 105598 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5782. Min Act: -0.0001

Data Index: 748537 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4697. Min Act: -0.0001

Data Index: 968603 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4671. Min Act: -0.0001

Data Index: 1097651 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4543. Min Act: -0.0001

Data Index: 901683 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4810. Min Act: -0.0001

Data Index: 791117 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4698. Min Act: -0.0001

Data Index: 1076889 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4774. Min Act: -0.0001

Data Index: 508865 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4612. Min Act: -0.0000

Data Index: 212096 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4437. Min Act: -0.0001

Data Index: 545061 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4089. Min Act: -0.0001

Data Index: 1253211 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4398. Min Act: -0.0001

Data Index: 968671 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4498. Min Act: -0.0001

Data Index: 1023493 (C4 (Web Text))

Max Activating Token Index: 771