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

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

Neuron 1150 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0085. Min Act: -0.0006

Data Index: 875704 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1066598 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0068. Min Act: -0.0006

Data Index: 783020 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0067. Min Act: -0.0006

Data Index: 30119 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0067. Min Act: -0.0006

Data Index: 734672 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0068. Min Act: -0.0006

Data Index: 434854 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1202343 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0066. Min Act: -0.0006

Data Index: 558349 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0065. Min Act: -0.0006

Data Index: 552695 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0064. Min Act: -0.0006

Data Index: 953234 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0065. Min Act: -0.0006

Data Index: 641469 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0066. Min Act: -0.0006

Data Index: 758029 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0067. Min Act: -0.0006

Data Index: 571925 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1121426 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0064. Min Act: -0.0006

Data Index: 265760 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0064. Min Act: -0.0006

Data Index: 286995 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1232281 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0064. Min Act: -0.0006

Data Index: 534383 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1018429 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0063. Min Act: -0.0006

Data Index: 222098 (C4 (Web Text))

Max Activating Token Index: 37