Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6125 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.8103. Min Act: -0.0002

Data Index: 607996 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7742. Min Act: -0.0002

Data Index: 1004329 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7598. Min Act: -0.0002

Data Index: 1272377 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7470. Min Act: -0.0002

Data Index: 1145001 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7290. Min Act: -0.0002

Data Index: 306136 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7152. Min Act: -0.0002

Data Index: 1099703 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7033. Min Act: -0.0002

Data Index: 59527 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7060. Min Act: -0.0002

Data Index: 1216691 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7181. Min Act: -0.0002

Data Index: 79765 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7069. Min Act: -0.0002

Data Index: 800314 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7011. Min Act: -0.0002

Data Index: 782286 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7003. Min Act: -0.0002

Data Index: 69030 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7053. Min Act: -0.0002

Data Index: 957412 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6842. Min Act: -0.0002

Data Index: 984085 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6976. Min Act: -0.0002

Data Index: 902273 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6900. Min Act: -0.0002

Data Index: 811324 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7057. Min Act: -0.0002

Data Index: 705263 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7041. Min Act: -0.0002

Data Index: 316693 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6926. Min Act: -0.0002

Data Index: 525802 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7027. Min Act: -0.0002

Data Index: 477754 (C4 (Web Text))

Max Activating Token Index: 436