Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1630 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0081. Min Act: -0.0006

Data Index: 940291 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1043517 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0070. Min Act: -0.0006

Data Index: 947817 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1340526 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0068. Min Act: -0.0006

Data Index: 137294 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1094983 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1330965 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0067. Min Act: -0.0006

Data Index: 940550 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0067. Min Act: -0.0006

Data Index: 280531 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0065. Min Act: -0.0006

Data Index: 337714 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0065. Min Act: -0.0006

Data Index: 112522 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0064. Min Act: -0.0006

Data Index: 89802 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0064. Min Act: -0.0006

Data Index: 55193 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1016566 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0062. Min Act: -0.0006

Data Index: 870160 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0064. Min Act: -0.0006

Data Index: 892674 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0062. Min Act: -0.0006

Data Index: 913894 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0062. Min Act: -0.0006

Data Index: 454276 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0062. Min Act: -0.0006

Data Index: 170943 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1315652 (C4 (Web Text))

Max Activating Token Index: 1001