Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4780 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1112347 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4161. Min Act: -0.0000

Data Index: 520536 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3828. Min Act: -0.0000

Data Index: 639958 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4027. Min Act: -0.0000

Data Index: 302298 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1341182 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1316962 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1357958 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3643. Min Act: -0.0000

Data Index: 703101 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1226236 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3534. Min Act: -0.0000

Data Index: 14421 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3612. Min Act: -0.0000

Data Index: 611824 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3450. Min Act: -0.0000

Data Index: 347822 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3547. Min Act: -0.0000

Data Index: 817455 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1060802 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1271236 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2997. Min Act: -0.0000

Data Index: 121594 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3011. Min Act: -0.0000

Data Index: 661684 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2868. Min Act: -0.0000

Data Index: 872087 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2937. Min Act: -0.0000

Data Index: 132262 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2781. Min Act: -0.0000

Data Index: 946096 (C4 (Web Text))

Max Activating Token Index: 800