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

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

Neuron 4376 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0067. Min Range: -3.0067

Max Act: 3.0067. Min Act: -0.0000

Data Index: 672058 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.4570. Min Act: -0.0000

Data Index: 222260 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.3773. Min Act: -0.0000

Data Index: 371397 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.2136. Min Act: -0.0000

Data Index: 581144 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.1825. Min Act: -0.0000

Data Index: 748748 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.2850. Min Act: -0.0000

Data Index: 97116 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.1015. Min Act: -0.0000

Data Index: 724297 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.1020. Min Act: -0.0000

Data Index: 581734 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.8603. Min Act: -0.0000

Data Index: 1046325 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.9576. Min Act: -0.0000

Data Index: 1219045 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.9322. Min Act: -0.0000

Data Index: 1127394 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.8258. Min Act: -0.0000

Data Index: 1224516 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.8230. Min Act: -0.0000

Data Index: 47956 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.9306. Min Act: -0.0000

Data Index: 562671 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.9105. Min Act: -0.0000

Data Index: 391023 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.8966. Min Act: -0.0000

Data Index: 239593 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.8982. Min Act: -0.0000

Data Index: 745025 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.8876. Min Act: -0.0000

Data Index: 449249 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.8773. Min Act: -0.0000

Data Index: 116037 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.0067. Min Range: -3.0067

Max Act: 1.8599. Min Act: -0.0000

Data Index: 851074 (C4 (Web Text))

Max Activating Token Index: 97