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

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

Neuron 2092 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6547. Min Range: -2.6547

Max Act: 2.6547. Min Act: -0.0000

Data Index: 1124378 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.9195. Min Act: -0.0000

Data Index: 913565 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.8486. Min Act: -0.0000

Data Index: 294654 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.7852. Min Act: -0.0000

Data Index: 75314 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.8835. Min Act: -0.0000

Data Index: 315293 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.4967. Min Act: -0.0000

Data Index: 460107 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.7172. Min Act: -0.0000

Data Index: 12222 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.5896. Min Act: -0.0000

Data Index: 1295278 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.6568. Min Act: -0.0000

Data Index: 839338 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.6515. Min Act: -0.0000

Data Index: 629236 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.4749. Min Act: -0.0000

Data Index: 786573 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.4882. Min Act: -0.0000

Data Index: 741846 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.5430. Min Act: -0.0000

Data Index: 1224949 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.4033. Min Act: -0.0000

Data Index: 737972 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.3552. Min Act: -0.0000

Data Index: 381625 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.2680. Min Act: -0.0000

Data Index: 965741 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.4768. Min Act: -0.0000

Data Index: 677851 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.3945. Min Act: -0.0000

Data Index: 1069773 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.2974. Min Act: -0.0000

Data Index: 916521 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 2.6547. Min Range: -2.6547

Max Act: 1.2863. Min Act: -0.0000

Data Index: 737759 (C4 (Web Text))

Max Activating Token Index: 623