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

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

Neuron 4317 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: 0.2752. Min Range: -0.2752

Max Act: 0.2752. Min Act: -0.0000

Data Index: 488244 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2602. Min Act: -0.0000

Data Index: 693380 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1270157 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1170678 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1341568 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2220. Min Act: -0.0000

Data Index: 314846 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1861. Min Act: -0.0000

Data Index: 302635 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2123. Min Act: -0.0000

Data Index: 715310 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2152. Min Act: -0.0000

Data Index: 921962 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1971. Min Act: -0.0000

Data Index: 773867 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2073. Min Act: -0.0000

Data Index: 455066 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1375513 (Python Code)

Max Activating Token Index: 973

Text #12

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1874. Min Act: -0.0000

Data Index: 163669 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1033897 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1911. Min Act: -0.0000

Data Index: 226223 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1163726 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1341228 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1918. Min Act: -0.0000

Data Index: 911495 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2031. Min Act: -0.0000

Data Index: 337881 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1846. Min Act: -0.0000

Data Index: 253333 (C4 (Web Text))

Max Activating Token Index: 554