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

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

Neuron 3362 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.9336. Min Act: -0.0000

Data Index: 393198 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.6088. Min Act: -0.0000

Data Index: 871158 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.4460. Min Act: -0.0000

Data Index: 474761 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.4072. Min Act: -0.0000

Data Index: 1414236 (Python Code)

Max Activating Token Index: 896

Text #4

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.3176. Min Act: -0.0000

Data Index: 242871 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.3539. Min Act: -0.0000

Data Index: 1617656 (Python Code)

Max Activating Token Index: 992

Text #6

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.3769. Min Act: -0.0000

Data Index: 1580588 (Python Code)

Max Activating Token Index: 941

Text #7

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.3464. Min Act: -0.0000

Data Index: 1275359 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.3042. Min Act: -0.0000

Data Index: 468064 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1228859 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.2811. Min Act: -0.0000

Data Index: 525573 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.2882. Min Act: -0.0000

Data Index: 737634 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.2058. Min Act: -0.0000

Data Index: 1305997 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.2445. Min Act: -0.0000

Data Index: 707139 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.2608. Min Act: -0.0000

Data Index: 481375 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1377754 (Python Code)

Max Activating Token Index: 984

Text #16

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.2012. Min Act: -0.0000

Data Index: 597632 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.2689. Min Act: -0.0000

Data Index: 671661 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1621221 (Python Code)

Max Activating Token Index: 883

Text #19

Max Range: 1.9336. Min Range: -1.9336

Max Act: 1.2112. Min Act: -0.0000

Data Index: 576780 (C4 (Web Text))

Max Activating Token Index: 312