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

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

Neuron 1440 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: 0.3516. Min Range: -0.3516

Max Act: 0.3516. Min Act: -0.0000

Data Index: 10959 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3507. Min Act: -0.0001

Data Index: 1307739 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3267. Min Act: -0.0001

Data Index: 278010 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2925. Min Act: -0.0001

Data Index: 447900 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2880. Min Act: -0.0001

Data Index: 1081895 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3099. Min Act: -0.0001

Data Index: 325416 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2697. Min Act: -0.0000

Data Index: 759117 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2895. Min Act: -0.0000

Data Index: 865845 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1288107 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2689. Min Act: -0.0000

Data Index: 383963 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2632. Min Act: -0.0001

Data Index: 572620 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2655. Min Act: -0.0000

Data Index: 386844 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2744. Min Act: -0.0001

Data Index: 634116 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1259273 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2547. Min Act: -0.0000

Data Index: 55136 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2565. Min Act: -0.0001

Data Index: 715542 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2682. Min Act: -0.0001

Data Index: 499322 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2572. Min Act: -0.0001

Data Index: 223533 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2577. Min Act: -0.0000

Data Index: 722123 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2678. Min Act: -0.0001

Data Index: 608674 (C4 (Web Text))

Max Activating Token Index: 733