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

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

Neuron 1325 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: 2.7705. Min Range: -2.7705

Max Act: 2.7705. Min Act: -0.0000

Data Index: 1011679 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 2.7705. Min Range: -2.7705

Max Act: 2.0277. Min Act: 0.0001

Data Index: 154312 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 2.7705. Min Range: -2.7705

Max Act: 2.1709. Min Act: -0.0000

Data Index: 958865 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 2.7705. Min Range: -2.7705

Max Act: 2.0436. Min Act: -0.0000

Data Index: 880423 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.9243. Min Act: -0.0000

Data Index: 989670 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.9507. Min Act: -0.0000

Data Index: 1007030 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.8718. Min Act: -0.0000

Data Index: 882654 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.8508. Min Act: -0.0000

Data Index: 140505 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.6817. Min Act: 0.0000

Data Index: 898624 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.6593. Min Act: 0.0000

Data Index: 100197 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.6149. Min Act: -0.0000

Data Index: 1146498 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.6254. Min Act: -0.0000

Data Index: 239542 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.6982. Min Act: -0.0000

Data Index: 50383 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.6019. Min Act: -0.0000

Data Index: 1432598 (Python Code)

Max Activating Token Index: 876

Text #14

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.5657. Min Act: 0.0000

Data Index: 1354928 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.4557. Min Act: -0.0000

Data Index: 320305 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.5481. Min Act: -0.0000

Data Index: 407647 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.5338. Min Act: -0.0000

Data Index: 507330 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.6192. Min Act: -0.0000

Data Index: 390707 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 2.7705. Min Range: -2.7705

Max Act: 1.5816. Min Act: -0.0000

Data Index: 137322 (C4 (Web Text))

Max Activating Token Index: 102