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

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

Neuron 3700 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0985. Min Act: -0.0000

Data Index: 22751 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0944. Min Act: -0.0000

Data Index: 200667 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0983. Min Act: -0.0000

Data Index: 647927 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1225624 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0962. Min Act: -0.0000

Data Index: 172494 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0884. Min Act: -0.0000

Data Index: 460460 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0956. Min Act: -0.0000

Data Index: 967786 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0875. Min Act: -0.0000

Data Index: 114261 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1280054 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0890. Min Act: -0.0000

Data Index: 836534 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0921. Min Act: -0.0000

Data Index: 243702 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1017404 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1258328 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0980. Min Act: -0.0000

Data Index: 992334 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0822. Min Act: -0.0000

Data Index: 444195 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0878. Min Act: -0.0000

Data Index: 709123 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0854. Min Act: -0.0000

Data Index: 592624 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1170525 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0855. Min Act: -0.0000

Data Index: 836169 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0854. Min Act: -0.0000

Data Index: 687285 (C4 (Web Text))

Max Activating Token Index: 442