Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2090 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.4863. Min Act: -0.0000

Data Index: 726330 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.5519. Min Act: -0.0000

Data Index: 1151635 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.5148. Min Act: -0.0000

Data Index: 305570 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.5149. Min Act: -0.0000

Data Index: 921868 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.4642. Min Act: -0.0000

Data Index: 1201460 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.3398. Min Act: -0.0000

Data Index: 240152 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.3326. Min Act: -0.0000

Data Index: 20758 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.4134. Min Act: -0.0000

Data Index: 800834 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.3784. Min Act: -0.0000

Data Index: 1320772 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.5121. Min Act: -0.0000

Data Index: 973810 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.3083. Min Act: -0.0000

Data Index: 494776 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.2595. Min Act: -0.0000

Data Index: 340424 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.3191. Min Act: -0.0000

Data Index: 378736 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.3361. Min Act: -0.0000

Data Index: 339565 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1192604 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.3119. Min Act: -0.0000

Data Index: 500888 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.3558. Min Act: -0.0000

Data Index: 320282 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1324549 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1278530 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.5519. Min Range: -1.5519

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1111704 (C4 (Web Text))

Max Activating Token Index: 310