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

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

Neuron 2514 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8791. Min Act: -0.0001

Data Index: 65024 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7944. Min Act: -0.0001

Data Index: 373851 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7398. Min Act: -0.0001

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7491. Min Act: -0.0001

Data Index: 585266 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.6441. Min Act: -0.0001

Data Index: 1219277 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.6374. Min Act: -0.0001

Data Index: 1238995 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.6444. Min Act: -0.0001

Data Index: 593025 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.6041. Min Act: -0.0001

Data Index: 203230 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.6182. Min Act: -0.0001

Data Index: 770264 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.6766. Min Act: -0.0001

Data Index: 906418 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.5833. Min Act: -0.0001

Data Index: 220347 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.6132. Min Act: -0.0001

Data Index: 1214731 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.5798. Min Act: -0.0001

Data Index: 82474 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.5888. Min Act: -0.0001

Data Index: 873990 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.5932. Min Act: -0.0001

Data Index: 497642 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.5730. Min Act: -0.0001

Data Index: 1145442 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.5523. Min Act: -0.0001

Data Index: 831510 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.5794. Min Act: -0.0001

Data Index: 542331 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.6024. Min Act: -0.0001

Data Index: 960739 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.5906. Min Act: -0.0001

Data Index: 806761 (C4 (Web Text))

Max Activating Token Index: 57