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

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

Neuron 3013 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.3636. Min Act: -0.0000

Data Index: 925764 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.3649. Min Act: -0.0001

Data Index: 770829 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.3124. Min Act: -0.0000

Data Index: 73643 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.3147. Min Act: -0.0000

Data Index: 715996 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.3118. Min Act: -0.0001

Data Index: 70967 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.3014. Min Act: -0.0001

Data Index: 488777 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.3185. Min Act: -0.0000

Data Index: 890943 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2875. Min Act: -0.0000

Data Index: 806391 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2977. Min Act: -0.0000

Data Index: 197575 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2884. Min Act: -0.0001

Data Index: 1100499 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.3041. Min Act: -0.0001

Data Index: 964160 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2914. Min Act: -0.0000

Data Index: 647126 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1176955 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2919. Min Act: -0.0001

Data Index: 945448 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2914. Min Act: -0.0000

Data Index: 975762 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1024165 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1157648 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2861. Min Act: -0.0001

Data Index: 554085 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2762. Min Act: -0.0001

Data Index: 1178811 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2757. Min Act: -0.0001

Data Index: 753907 (C4 (Web Text))

Max Activating Token Index: 930