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

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

Neuron 3856 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: 0.3550. Min Range: -0.3550

Max Act: 0.3550. Min Act: -0.0001

Data Index: 1620389 (Python Code)

Max Activating Token Index: 644

Text #1

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1363430 (Python Code)

Max Activating Token Index: 89

Text #2

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3320. Min Act: -0.0001

Data Index: 1614486 (Python Code)

Max Activating Token Index: 598

Text #3

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3172. Min Act: -0.0001

Data Index: 1567796 (Python Code)

Max Activating Token Index: 798

Text #4

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1454233 (Python Code)

Max Activating Token Index: 518

Text #5

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3051. Min Act: -0.0001

Data Index: 1650798 (Python Code)

Max Activating Token Index: 327

Text #6

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1524636 (Python Code)

Max Activating Token Index: 871

Text #7

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3003. Min Act: -0.0001

Data Index: 1656733 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1572356 (Python Code)

Max Activating Token Index: 149

Text #9

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1504195 (Python Code)

Max Activating Token Index: 58

Text #10

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3130. Min Act: -0.0001

Data Index: 1474723 (Python Code)

Max Activating Token Index: 920

Text #11

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1618568 (Python Code)

Max Activating Token Index: 292

Text #12

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1580436 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2811. Min Act: -0.0001

Data Index: 1621698 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1402908 (Python Code)

Max Activating Token Index: 243

Text #15

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2817. Min Act: -0.0001

Data Index: 1437516 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1603816 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1398563 (Python Code)

Max Activating Token Index: 502

Text #18

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1530037 (Python Code)

Max Activating Token Index: 524

Text #19

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1542353 (Python Code)

Max Activating Token Index: 988