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

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

Neuron 3155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.7220. Min Act: -0.0000

Data Index: 288720 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.5775. Min Act: -0.0000

Data Index: 514888 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.5197. Min Act: -0.0000

Data Index: 375677 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.5669. Min Act: -0.0000

Data Index: 970522 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1075778 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4797. Min Act: -0.0000

Data Index: 223578 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4648. Min Act: -0.0000

Data Index: 693462 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1252731 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.3620. Min Act: -0.0000

Data Index: 780045 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1094820 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1255995 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1394971 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1526416 (Python Code)

Max Activating Token Index: 618

Text #13

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.2947. Min Act: -0.0000

Data Index: 46349 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1413236 (Python Code)

Max Activating Token Index: 1006

Text #15

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.2905. Min Act: -0.0000

Data Index: 755237 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.2555. Min Act: -0.0000

Data Index: 577540 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1020927 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.2742. Min Act: -0.0000

Data Index: 813143 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1099205 (C4 (Web Text))

Max Activating Token Index: 755