Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 696 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.3009. Min Act: -0.0001

Data Index: 827942 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2420. Min Act: -0.0001

Data Index: 359095 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2241. Min Act: -0.0001

Data Index: 270307 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2160. Min Act: -0.0001

Data Index: 1255229 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2196. Min Act: -0.0001

Data Index: 209188 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2105. Min Act: -0.0001

Data Index: 663448 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2191. Min Act: -0.0001

Data Index: 964026 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2197. Min Act: -0.0001

Data Index: 1287860 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2201. Min Act: -0.0001

Data Index: 361841 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2119. Min Act: -0.0001

Data Index: 515067 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2041. Min Act: -0.0001

Data Index: 192722 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1969. Min Act: -0.0001

Data Index: 145303 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1122343 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2002. Min Act: -0.0001

Data Index: 625841 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2014. Min Act: -0.0001

Data Index: 434811 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1210800 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1849. Min Act: -0.0001

Data Index: 698161 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2062. Min Act: -0.0001

Data Index: 197021 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1752. Min Act: -0.0001

Data Index: 345576 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1959. Min Act: -0.0001

Data Index: 418747 (C4 (Web Text))

Max Activating Token Index: 350