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

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

Neuron 1766 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2082. Min Range: -5.2082

Max Act: 5.2082. Min Act: -0.0000

Data Index: 1269174 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 5.2082. Min Range: -5.2082

Max Act: 4.8172. Min Act: -0.0000

Data Index: 1106179 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 5.2082. Min Range: -5.2082

Max Act: 4.4158. Min Act: -0.0000

Data Index: 366181 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 5.2082. Min Range: -5.2082

Max Act: 4.1270. Min Act: -0.0000

Data Index: 1204387 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 5.2082. Min Range: -5.2082

Max Act: 4.2572. Min Act: -0.0000

Data Index: 1298439 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 5.2082. Min Range: -5.2082

Max Act: 4.2567. Min Act: -0.0000

Data Index: 897411 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 5.2082. Min Range: -5.2082

Max Act: 4.0566. Min Act: -0.0000

Data Index: 805926 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 5.2082. Min Range: -5.2082

Max Act: 4.0486. Min Act: -0.0000

Data Index: 745169 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 5.2082. Min Range: -5.2082

Max Act: 4.0288. Min Act: -0.0000

Data Index: 545316 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.9524. Min Act: -0.0000

Data Index: 976513 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.8507. Min Act: -0.0000

Data Index: 519324 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.6795. Min Act: -0.0000

Data Index: 687693 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.6677. Min Act: -0.0000

Data Index: 985805 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.6145. Min Act: -0.0000

Data Index: 441274 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.6646. Min Act: -0.0000

Data Index: 1342473 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.5220. Min Act: -0.0000

Data Index: 793901 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.2113. Min Act: -0.0000

Data Index: 706173 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.4314. Min Act: -0.0000

Data Index: 1302548 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.3924. Min Act: -0.0000

Data Index: 500441 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 5.2082. Min Range: -5.2082

Max Act: 3.3815. Min Act: -0.0000

Data Index: 597264 (C4 (Web Text))

Max Activating Token Index: 758