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

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

Neuron 2972 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7614. Min Range: -3.7614

Max Act: 3.7614. Min Act: -0.0000

Data Index: 1198757 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 3.7614. Min Range: -3.7614

Max Act: 3.3612. Min Act: -0.0000

Data Index: 852833 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 3.7614. Min Range: -3.7614

Max Act: 3.6673. Min Act: -0.0000

Data Index: 490699 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 3.7614. Min Range: -3.7614

Max Act: 3.4689. Min Act: -0.0000

Data Index: 461276 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 3.7614. Min Range: -3.7614

Max Act: 3.3957. Min Act: -0.0000

Data Index: 27670 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 3.7614. Min Range: -3.7614

Max Act: 3.2899. Min Act: -0.0000

Data Index: 926526 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 3.7614. Min Range: -3.7614

Max Act: 3.5519. Min Act: -0.0000

Data Index: 917587 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 3.7614. Min Range: -3.7614

Max Act: 3.2485. Min Act: -0.0000

Data Index: 1294265 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 3.7614. Min Range: -3.7614

Max Act: 2.8854. Min Act: -0.0000

Data Index: 331579 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 3.7614. Min Range: -3.7614

Max Act: 2.8796. Min Act: -0.0000

Data Index: 1074095 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 3.7614. Min Range: -3.7614

Max Act: 2.9849. Min Act: -0.0000

Data Index: 590610 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 3.7614. Min Range: -3.7614

Max Act: 2.9634. Min Act: -0.0000

Data Index: 969831 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 3.7614. Min Range: -3.7614

Max Act: 2.9329. Min Act: -0.0000

Data Index: 452483 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 3.7614. Min Range: -3.7614

Max Act: 2.8536. Min Act: -0.0000

Data Index: 644929 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 3.7614. Min Range: -3.7614

Max Act: 3.3059. Min Act: -0.0000

Data Index: 1208098 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 3.7614. Min Range: -3.7614

Max Act: 3.1322. Min Act: -0.0000

Data Index: 1212936 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 3.7614. Min Range: -3.7614

Max Act: 2.9693. Min Act: -0.0000

Data Index: 840175 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 3.7614. Min Range: -3.7614

Max Act: 2.9533. Min Act: -0.0000

Data Index: 1217744 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 3.7614. Min Range: -3.7614

Max Act: 2.6002. Min Act: -0.0000

Data Index: 578797 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 3.7614. Min Range: -3.7614

Max Act: 2.5593. Min Act: -0.0000

Data Index: 593410 (C4 (Web Text))

Max Activating Token Index: 692