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

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

Neuron 909 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: 1.8758. Min Range: -1.8758

Max Act: 1.8657. Min Act: -0.0000

Data Index: 1552637 (Python Code)

Max Activating Token Index: 786

Text #1

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.8438. Min Act: -0.0000

Data Index: 923312 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1436681 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.7525. Min Act: -0.0000

Data Index: 1011180 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.8758. Min Act: -0.0000

Data Index: 771473 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.6906. Min Act: -0.0000

Data Index: 1152286 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.7505. Min Act: -0.0000

Data Index: 379001 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1262762 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.5711. Min Act: -0.0000

Data Index: 333777 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.6734. Min Act: -0.0000

Data Index: 124837 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.6473. Min Act: -0.0000

Data Index: 1197771 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.5121. Min Act: -0.0000

Data Index: 513744 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.4766. Min Act: -0.0000

Data Index: 1595779 (Python Code)

Max Activating Token Index: 390

Text #13

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.5557. Min Act: -0.0000

Data Index: 484951 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.5382. Min Act: -0.0000

Data Index: 1209384 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.5100. Min Act: -0.0000

Data Index: 91301 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.4855. Min Act: -0.0000

Data Index: 832089 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.4638. Min Act: -0.0000

Data Index: 1544053 (Python Code)

Max Activating Token Index: 925

Text #18

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.3768. Min Act: -0.0000

Data Index: 706570 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.3545. Min Act: -0.0000

Data Index: 1067935 (C4 (Web Text))

Max Activating Token Index: 245