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

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

Neuron 1455 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: 0.8512. Min Range: -0.8512

Max Act: 0.8512. Min Act: -0.0001

Data Index: 166264 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.8209. Min Act: -0.0001

Data Index: 303822 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7487. Min Act: -0.0001

Data Index: 188708 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6874. Min Act: -0.0001

Data Index: 58794 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.8050. Min Act: -0.0001

Data Index: 937070 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7840. Min Act: -0.0001

Data Index: 197068 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7505. Min Act: -0.0001

Data Index: 65330 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7788. Min Act: -0.0001

Data Index: 1139052 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7349. Min Act: -0.0001

Data Index: 711070 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7365. Min Act: -0.0001

Data Index: 829356 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7121. Min Act: -0.0001

Data Index: 1209581 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7582. Min Act: -0.0001

Data Index: 367269 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7473. Min Act: -0.0001

Data Index: 1129651 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6842. Min Act: -0.0001

Data Index: 1226603 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7106. Min Act: -0.0001

Data Index: 529556 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6869. Min Act: -0.0001

Data Index: 424231 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6495. Min Act: -0.0001

Data Index: 1110582 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6437. Min Act: -0.0001

Data Index: 1173754 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7055. Min Act: -0.0001

Data Index: 739903 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6758. Min Act: -0.0001

Data Index: 1024986 (C4 (Web Text))

Max Activating Token Index: 764