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

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

Neuron 3270 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2677. Min Act: -0.0001

Data Index: 1026997 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2752. Min Act: -0.0001

Data Index: 422460 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1261029 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2494. Min Act: -0.0001

Data Index: 1152657 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2488. Min Act: -0.0001

Data Index: 667405 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2550. Min Act: -0.0001

Data Index: 1403618 (Python Code)

Max Activating Token Index: 646

Text #6

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2510. Min Act: -0.0001

Data Index: 558369 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2544. Min Act: -0.0001

Data Index: 927078 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2411. Min Act: -0.0001

Data Index: 879685 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2416. Min Act: -0.0001

Data Index: 444825 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2229. Min Act: -0.0001

Data Index: 1094557 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2219. Min Act: -0.0001

Data Index: 80468 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2557. Min Act: -0.0001

Data Index: 468192 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2347. Min Act: -0.0001

Data Index: 671973 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2327. Min Act: -0.0001

Data Index: 388486 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2179. Min Act: -0.0001

Data Index: 698786 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2212. Min Act: -0.0001

Data Index: 527301 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2190. Min Act: -0.0001

Data Index: 685757 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2081. Min Act: -0.0001

Data Index: 422587 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2230. Min Act: -0.0001

Data Index: 723356 (C4 (Web Text))

Max Activating Token Index: 968