Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1740 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.9216. Min Act: -0.0001

Data Index: 771733 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.0495. Min Range: -1.0495

Max Act: 1.0495. Min Act: -0.0001

Data Index: 164065 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8718. Min Act: -0.0001

Data Index: 1242077 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8605. Min Act: -0.0001

Data Index: 147770 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7590. Min Act: -0.0001

Data Index: 206312 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7923. Min Act: -0.0001

Data Index: 132586 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7230. Min Act: -0.0001

Data Index: 748584 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7716. Min Act: -0.0000

Data Index: 231189 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8191. Min Act: -0.0001

Data Index: 897889 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7381. Min Act: -0.0001

Data Index: 758043 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7646. Min Act: -0.0001

Data Index: 485561 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7696. Min Act: -0.0000

Data Index: 482966 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7445. Min Act: -0.0001

Data Index: 398607 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7464. Min Act: -0.0000

Data Index: 712639 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6672. Min Act: -0.0001

Data Index: 1046363 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8063. Min Act: -0.0001

Data Index: 906666 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6972. Min Act: -0.0001

Data Index: 611664 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7252. Min Act: -0.0001

Data Index: 1156447 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7613. Min Act: -0.0001

Data Index: 1064456 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7553. Min Act: -0.0001

Data Index: 273620 (C4 (Web Text))

Max Activating Token Index: 961