Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3808 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.5400. Min Act: -0.0000

Data Index: 444331 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.5204. Min Act: -0.0000

Data Index: 30591 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4825. Min Act: -0.0000

Data Index: 468935 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4459. Min Act: -0.0000

Data Index: 996238 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4515. Min Act: -0.0000

Data Index: 880779 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3716. Min Act: -0.0000

Data Index: 843831 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3972. Min Act: -0.0000

Data Index: 669238 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3498. Min Act: -0.0000

Data Index: 246815 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3758. Min Act: -0.0000

Data Index: 947644 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3667. Min Act: -0.0000

Data Index: 964632 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3792. Min Act: -0.0000

Data Index: 340137 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3447. Min Act: -0.0000

Data Index: 546633 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3447. Min Act: -0.0000

Data Index: 2593 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3313. Min Act: -0.0000

Data Index: 814392 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3475. Min Act: -0.0000

Data Index: 67683 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3092. Min Act: -0.0000

Data Index: 966674 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3440. Min Act: -0.0000

Data Index: 952953 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3153. Min Act: -0.0000

Data Index: 307390 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3313. Min Act: -0.0000

Data Index: 415229 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1058975 (C4 (Web Text))

Max Activating Token Index: 44