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

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

Neuron 4656 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.2272. Min Act: -0.0000

Data Index: 1489930 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1411. Min Act: -0.0000

Data Index: 518670 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.6883. Min Act: -0.0000

Data Index: 121132 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.9718. Min Act: -0.0000

Data Index: 175825 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.2453. Min Act: -0.0000

Data Index: 1561214 (Python Code)

Max Activating Token Index: 363

Text #5

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.7048. Min Act: -0.0000

Data Index: 1532329 (Python Code)

Max Activating Token Index: 374

Text #6

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.6972. Min Act: -0.0000

Data Index: 1385065 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.6389. Min Act: -0.0000

Data Index: 1092455 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.7574. Min Act: -0.0000

Data Index: 195530 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.3766. Min Act: -0.0000

Data Index: 1348562 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.4479. Min Act: -0.0000

Data Index: 1583073 (Python Code)

Max Activating Token Index: 227

Text #11

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.5538. Min Act: -0.0000

Data Index: 85079 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.6710. Min Act: -0.0000

Data Index: 1504878 (Python Code)

Max Activating Token Index: 322

Text #13

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.4020. Min Act: -0.0000

Data Index: 693538 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.4058. Min Act: -0.0000

Data Index: 1506618 (Python Code)

Max Activating Token Index: 65

Text #15

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.4011. Min Act: -0.0000

Data Index: 446293 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.4932. Min Act: -0.0000

Data Index: 1504337 (Python Code)

Max Activating Token Index: 124

Text #17

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.5958. Min Act: -0.0000

Data Index: 965264 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.1947. Min Act: -0.0000

Data Index: 1078687 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.5538. Min Act: -0.0000

Data Index: 627785 (C4 (Web Text))

Max Activating Token Index: 423