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

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

Neuron 2034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1463. Min Range: -2.1463

Max Act: 2.0109. Min Act: -0.0000

Data Index: 357246 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.9967. Min Act: -0.0000

Data Index: 1188399 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 2.1463. Min Range: -2.1463

Max Act: 2.1107. Min Act: -0.0000

Data Index: 371949 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 2.1463. Min Range: -2.1463

Max Act: 2.1230. Min Act: -0.0000

Data Index: 1247202 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 2.1463. Min Range: -2.1463

Max Act: 2.0706. Min Act: -0.0000

Data Index: 1320147 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 2.1463. Min Range: -2.1463

Max Act: 2.0317. Min Act: -0.0000

Data Index: 381083 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 2.1463. Min Range: -2.1463

Max Act: 2.1289. Min Act: -0.0001

Data Index: 1280920 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.8711. Min Act: -0.0000

Data Index: 1317231 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.9440. Min Act: -0.0000

Data Index: 286207 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 2.1463. Min Range: -2.1463

Max Act: 2.1463. Min Act: -0.0000

Data Index: 763562 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 2.1463. Min Range: -2.1463

Max Act: 2.0329. Min Act: -0.0000

Data Index: 1017064 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.8093. Min Act: -0.0000

Data Index: 1270981 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.7800. Min Act: -0.0000

Data Index: 404298 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.7755. Min Act: -0.0000

Data Index: 728815 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.8715. Min Act: -0.0000

Data Index: 581776 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.9626. Min Act: -0.0000

Data Index: 913501 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.6333. Min Act: -0.0000

Data Index: 652573 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.9197. Min Act: -0.0000

Data Index: 453063 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.7914. Min Act: -0.0000

Data Index: 1105162 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 2.1463. Min Range: -2.1463

Max Act: 1.7719. Min Act: -0.0000

Data Index: 427683 (C4 (Web Text))

Max Activating Token Index: 350