Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 968 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.9961. Min Range: -6.9961

Max Act: 6.9961. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 6.9961. Min Range: -6.9961

Max Act: 6.6416. Min Act: -0.0000

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 6.9961. Min Range: -6.9961

Max Act: 6.3466. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 6.9961. Min Range: -6.9961

Max Act: 6.0726. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.7430. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.8439. Min Act: -0.0000

Data Index: 1135148 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.6122. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.6462. Min Act: -0.0000

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.4756. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.6017. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.5358. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.5107. Min Act: -0.0000

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.4935. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.4646. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.4447. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.3454. Min Act: -0.0000

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.3201. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.4166. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 6.9961. Min Range: -6.9961

Max Act: 5.1506. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 6.9961. Min Range: -6.9961

Max Act: 4.9814. Min Act: -0.0000

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 13