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

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

Neuron 3146 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.9329. Min Act: -0.0000

Data Index: 549066 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.7404. Min Act: -0.0000

Data Index: 76528 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1305023 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.6485. Min Act: -0.0000

Data Index: 16223 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.5310. Min Act: -0.0000

Data Index: 506659 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.5314. Min Act: -0.0000

Data Index: 457120 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.5435. Min Act: -0.0000

Data Index: 673272 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1011009 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.4753. Min Act: -0.0000

Data Index: 489681 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.4072. Min Act: -0.0000

Data Index: 442450 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1212886 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.4189. Min Act: -0.0000

Data Index: 814305 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.3996. Min Act: -0.0000

Data Index: 125977 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1106948 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.3978. Min Act: -0.0000

Data Index: 344275 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.3820. Min Act: -0.0000

Data Index: 284419 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.3817. Min Act: 0.0000

Data Index: 546086 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.4052. Min Act: -0.0000

Data Index: 789071 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.3905. Min Act: -0.0000

Data Index: 295119 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.9329. Min Range: -0.9329

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1163854 (C4 (Web Text))

Max Activating Token Index: 612