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

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

Neuron 5813 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: 1.2353. Min Range: -1.2353

Max Act: 1.2353. Min Act: -0.0000

Data Index: 975528 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.2118. Min Act: -0.0000

Data Index: 565056 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.1331. Min Act: -0.0000

Data Index: 153832 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.1626. Min Act: -0.0000

Data Index: 728673 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.1517. Min Act: -0.0000

Data Index: 297420 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0226. Min Act: -0.0000

Data Index: 947930 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9973. Min Act: -0.0000

Data Index: 1279375 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0389. Min Act: -0.0000

Data Index: 856066 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0001. Min Act: -0.0000

Data Index: 893552 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0525. Min Act: -0.0000

Data Index: 472351 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0122. Min Act: -0.0000

Data Index: 564068 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1573155 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9578. Min Act: -0.0000

Data Index: 284934 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1638328 (Python Code)

Max Activating Token Index: 767

Text #14

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1054876 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9174. Min Act: -0.0000

Data Index: 966556 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9420. Min Act: -0.0000

Data Index: 266173 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.8527. Min Act: -0.0000

Data Index: 697392 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9113. Min Act: -0.0000

Data Index: 889161 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9074. Min Act: -0.0000

Data Index: 780094 (C4 (Web Text))

Max Activating Token Index: 109