Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 781 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0003

Data Index: 50000 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0078. Min Act: -0.0003

Data Index: 253277 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0075. Min Act: -0.0003

Data Index: 112871 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1089197 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1203785 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0003

Data Index: 988123 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1110498 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1199269 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0003

Data Index: 309337 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 202625 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0069. Min Act: -0.0003

Data Index: 355648 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 200336 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 427762 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 697355 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0067. Min Act: -0.0002

Data Index: 805021 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1222391 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0067. Min Act: -0.0003

Data Index: 483777 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1026530 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1026382 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0066. Min Act: -0.0003

Data Index: 422903 (C4 (Web Text))

Max Activating Token Index: 85