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

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

Neuron 3615 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1163688 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1200756 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5627. Min Act: -0.0000

Data Index: 567665 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5368. Min Act: -0.0000

Data Index: 731261 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1262127 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5006. Min Act: -0.0000

Data Index: 9203 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1285114 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1138732 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4368. Min Act: -0.0000

Data Index: 265591 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4547. Min Act: -0.0000

Data Index: 763562 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4463. Min Act: -0.0000

Data Index: 82553 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4375. Min Act: -0.0000

Data Index: 780749 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4246. Min Act: -0.0000

Data Index: 470591 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4373. Min Act: -0.0000

Data Index: 472589 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4342. Min Act: -0.0000

Data Index: 64850 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1263442 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1103517 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1262083 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4232. Min Act: -0.0000

Data Index: 883086 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4242. Min Act: -0.0000

Data Index: 613334 (C4 (Web Text))

Max Activating Token Index: 628