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

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

Neuron 2702 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1558673 (Python Code)

Max Activating Token Index: 465

Text #1

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1100. Min Act: -0.0001

Data Index: 950146 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1635807 (Python Code)

Max Activating Token Index: 126

Text #3

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1000. Min Act: -0.0001

Data Index: 504102 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0983. Min Act: -0.0001

Data Index: 473229 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1242494 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0981. Min Act: -0.0001

Data Index: 526817 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0920. Min Act: -0.0001

Data Index: 773885 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0980. Min Act: -0.0001

Data Index: 110741 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0999. Min Act: -0.0001

Data Index: 222900 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1205548 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0912. Min Act: -0.0001

Data Index: 682181 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0964. Min Act: -0.0001

Data Index: 953569 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0844. Min Act: -0.0001

Data Index: 456575 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1476457 (Python Code)

Max Activating Token Index: 966

Text #15

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0880. Min Act: -0.0001

Data Index: 935413 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1157360 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1029831 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1136351 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0868. Min Act: -0.0001

Data Index: 960691 (C4 (Web Text))

Max Activating Token Index: 376