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

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

Neuron 2848 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: 2.7244. Min Range: -2.7244

Max Act: 2.7244. Min Act: -0.0000

Data Index: 939044 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.4501. Min Act: -0.0000

Data Index: 16615 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.3670. Min Act: -0.0000

Data Index: 714637 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.3094. Min Act: -0.0000

Data Index: 268695 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.2673. Min Act: -0.0000

Data Index: 1252745 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.2383. Min Act: -0.0000

Data Index: 674794 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.2017. Min Act: -0.0000

Data Index: 192503 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.0557. Min Act: -0.0000

Data Index: 801204 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.0116. Min Act: -0.0000

Data Index: 390433 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.9263. Min Act: -0.0000

Data Index: 945282 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.9032. Min Act: -0.0000

Data Index: 490581 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.8990. Min Act: -0.0000

Data Index: 103669 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.7672. Min Act: -0.0000

Data Index: 657935 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.7710. Min Act: -0.0000

Data Index: 884833 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.8312. Min Act: -0.0000

Data Index: 643685 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.7161. Min Act: -0.0000

Data Index: 667161 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.8126. Min Act: -0.0000

Data Index: 747162 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.8156. Min Act: -0.0000

Data Index: 304322 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.7774. Min Act: -0.0000

Data Index: 322830 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 2.7244. Min Range: -2.7244

Max Act: 1.7697. Min Act: -0.0000

Data Index: 148868 (C4 (Web Text))

Max Activating Token Index: 102