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

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

Neuron 56 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1587172 (Python Code)

Max Activating Token Index: 318

Text #1

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1398658 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.7191. Min Act: -0.0001

Data Index: 1116807 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6650. Min Act: -0.0001

Data Index: 585567 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6611. Min Act: -0.0001

Data Index: 5254 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6760. Min Act: -0.0001

Data Index: 798195 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6193. Min Act: -0.0001

Data Index: 384927 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6808. Min Act: -0.0001

Data Index: 977341 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1521007 (Python Code)

Max Activating Token Index: 405

Text #9

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6110. Min Act: -0.0001

Data Index: 631342 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1400315 (Python Code)

Max Activating Token Index: 982

Text #11

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6119. Min Act: -0.0001

Data Index: 1149583 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6526. Min Act: -0.0001

Data Index: 1304151 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5462. Min Act: -0.0001

Data Index: 909286 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6093. Min Act: -0.0001

Data Index: 419775 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5351. Min Act: -0.0001

Data Index: 1428159 (Python Code)

Max Activating Token Index: 621

Text #16

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6163. Min Act: -0.0001

Data Index: 1062039 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6051. Min Act: -0.0001

Data Index: 116730 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5847. Min Act: -0.0001

Data Index: 1528916 (Python Code)

Max Activating Token Index: 248

Text #19

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5806. Min Act: -0.0001

Data Index: 82130 (C4 (Web Text))

Max Activating Token Index: 319