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

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

Neuron 1974 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3685. Min Act: -0.0000

Data Index: 202946 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1106402 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3066. Min Act: -0.0000

Data Index: 509013 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3002. Min Act: -0.0000

Data Index: 853859 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2979. Min Act: -0.0000

Data Index: 290006 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3290. Min Act: -0.0001

Data Index: 755065 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1334985 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2946. Min Act: -0.0000

Data Index: 956011 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2719. Min Act: -0.0000

Data Index: 449828 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2613. Min Act: -0.0000

Data Index: 34738 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2838. Min Act: -0.0001

Data Index: 1221748 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3102. Min Act: -0.0000

Data Index: 347354 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2868. Min Act: -0.0000

Data Index: 256497 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2819. Min Act: -0.0000

Data Index: 96837 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2814. Min Act: -0.0000

Data Index: 434541 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2901. Min Act: -0.0000

Data Index: 897688 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2897. Min Act: -0.0000

Data Index: 598654 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1281245 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2658. Min Act: -0.0001

Data Index: 301631 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1155057 (C4 (Web Text))

Max Activating Token Index: 793