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

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

Neuron 3003 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: 0.6465. Min Range: -0.6465

Max Act: 0.6465. Min Act: -0.0001

Data Index: 13968 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5614. Min Act: -0.0001

Data Index: 911466 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4511. Min Act: -0.0001

Data Index: 107373 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4422. Min Act: -0.0001

Data Index: 429984 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4141. Min Act: -0.0001

Data Index: 1025710 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4354. Min Act: -0.0001

Data Index: 1140970 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4292. Min Act: -0.0001

Data Index: 1269806 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4449. Min Act: -0.0001

Data Index: 1320934 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4314. Min Act: -0.0001

Data Index: 763049 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.3850. Min Act: -0.0001

Data Index: 927037 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4051. Min Act: -0.0001

Data Index: 1227551 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.3924. Min Act: -0.0001

Data Index: 750946 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4045. Min Act: -0.0001

Data Index: 447837 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.3857. Min Act: -0.0001

Data Index: 994390 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4095. Min Act: -0.0001

Data Index: 821517 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1264250 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.3897. Min Act: -0.0001

Data Index: 710700 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4019. Min Act: -0.0001

Data Index: 148804 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4259. Min Act: -0.0001

Data Index: 662476 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.3883. Min Act: -0.0001

Data Index: 1339064 (C4 (Web Text))

Max Activating Token Index: 141