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

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

Neuron 3023 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.7082. Min Act: -0.0001

Data Index: 1071768 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6815. Min Act: -0.0001

Data Index: 1183638 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6181. Min Act: -0.0001

Data Index: 1458719 (Python Code)

Max Activating Token Index: 771

Text #3

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6798. Min Act: -0.0001

Data Index: 198048 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1630510 (Python Code)

Max Activating Token Index: 129

Text #5

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6379. Min Act: -0.0001

Data Index: 1631911 (Python Code)

Max Activating Token Index: 747

Text #6

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6559. Min Act: -0.0001

Data Index: 1577171 (Python Code)

Max Activating Token Index: 386

Text #7

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6125. Min Act: -0.0001

Data Index: 1453492 (Python Code)

Max Activating Token Index: 585

Text #8

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6113. Min Act: -0.0000

Data Index: 868504 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6346. Min Act: -0.0001

Data Index: 1609121 (Python Code)

Max Activating Token Index: 548

Text #10

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6363. Min Act: -0.0001

Data Index: 1471648 (Python Code)

Max Activating Token Index: 467

Text #11

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6314. Min Act: -0.0001

Data Index: 1360200 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6485. Min Act: -0.0001

Data Index: 1534984 (Python Code)

Max Activating Token Index: 656

Text #13

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6226. Min Act: -0.0001

Data Index: 75980 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6369. Min Act: -0.0001

Data Index: 791945 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6215. Min Act: -0.0001

Data Index: 616926 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5951. Min Act: -0.0001

Data Index: 1487986 (Python Code)

Max Activating Token Index: 480

Text #17

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5746. Min Act: -0.0001

Data Index: 1481256 (Python Code)

Max Activating Token Index: 758

Text #18

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5920. Min Act: -0.0001

Data Index: 1458546 (Python Code)

Max Activating Token Index: 476

Text #19

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6058. Min Act: -0.0001

Data Index: 1536578 (Python Code)

Max Activating Token Index: 697