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

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

Neuron 1159 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: 4.0438. Min Range: -4.0438

Max Act: 4.0438. Min Act: -0.0000

Data Index: 97492 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.5188. Min Act: -0.0001

Data Index: 640505 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.5721. Min Act: -0.0001

Data Index: 824253 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.3274. Min Act: -0.0000

Data Index: 1306944 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.0483. Min Act: -0.0001

Data Index: 958690 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.0052. Min Act: -0.0000

Data Index: 721072 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.1470. Min Act: -0.0001

Data Index: 716791 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.1383. Min Act: -0.0001

Data Index: 637038 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.1008. Min Act: -0.0001

Data Index: 16593 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.2466. Min Act: -0.0000

Data Index: 862393 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 4.0438. Min Range: -4.0438

Max Act: 2.9450. Min Act: -0.0000

Data Index: 944582 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.0820. Min Act: -0.0001

Data Index: 846228 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 4.0438. Min Range: -4.0438

Max Act: 2.9145. Min Act: -0.0000

Data Index: 693366 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.1933. Min Act: -0.0001

Data Index: 1088094 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 4.0438. Min Range: -4.0438

Max Act: 2.9116. Min Act: -0.0001

Data Index: 417070 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.0460. Min Act: -0.0001

Data Index: 157907 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 4.0438. Min Range: -4.0438

Max Act: 2.9061. Min Act: -0.0000

Data Index: 445789 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 4.0438. Min Range: -4.0438

Max Act: 3.1672. Min Act: -0.0001

Data Index: 284010 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 4.0438. Min Range: -4.0438

Max Act: 2.9987. Min Act: -0.0000

Data Index: 607417 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 4.0438. Min Range: -4.0438

Max Act: 2.9737. Min Act: -0.0001

Data Index: 839533 (C4 (Web Text))

Max Activating Token Index: 118