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

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

Neuron 1294 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1331960 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 274211 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 8328 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1115409 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 870821 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 171779 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 144867 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 494235 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 795088 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 641316 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1086853 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 591814 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0003

Data Index: 45232 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0004

Data Index: 81616 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0004

Data Index: 1138500 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 607631 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1265056 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 698888 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1264365 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0004

Data Index: 1142609 (C4 (Web Text))

Max Activating Token Index: 518