Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 324 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.4224. Min Act: -0.0001

Data Index: 1612687 (Python Code)

Max Activating Token Index: 107

Text #1

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3732. Min Act: -0.0001

Data Index: 1550220 (Python Code)

Max Activating Token Index: 596

Text #2

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3160. Min Act: -0.0001

Data Index: 1492203 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3080. Min Act: -0.0001

Data Index: 1517940 (Python Code)

Max Activating Token Index: 916

Text #4

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2859. Min Act: -0.0001

Data Index: 1454386 (Python Code)

Max Activating Token Index: 78

Text #5

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1011988 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2625. Min Act: -0.0001

Data Index: 729652 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2792. Min Act: -0.0000

Data Index: 401186 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2643. Min Act: -0.0001

Data Index: 861714 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2566. Min Act: -0.0001

Data Index: 1388029 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1538547 (Python Code)

Max Activating Token Index: 945

Text #11

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2641. Min Act: -0.0001

Data Index: 1617807 (Python Code)

Max Activating Token Index: 683

Text #12

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1127387 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2588. Min Act: -0.0001

Data Index: 1600505 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2437. Min Act: -0.0001

Data Index: 1391138 (Python Code)

Max Activating Token Index: 757

Text #15

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2347. Min Act: -0.0001

Data Index: 1602042 (Python Code)

Max Activating Token Index: 615

Text #16

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1591653 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1638240 (Python Code)

Max Activating Token Index: 802

Text #18

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1646683 (Python Code)

Max Activating Token Index: 653

Text #19

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1465017 (Python Code)

Max Activating Token Index: 111