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

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

Neuron 3627 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: 0.4390. Min Range: -0.4390

Max Act: 0.4012. Min Act: -0.0001

Data Index: 1511930 (Python Code)

Max Activating Token Index: 179

Text #1

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.4390. Min Act: -0.0001

Data Index: 1589269 (Python Code)

Max Activating Token Index: 806

Text #2

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3885. Min Act: -0.0001

Data Index: 1611147 (Python Code)

Max Activating Token Index: 152

Text #3

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.4126. Min Act: -0.0001

Data Index: 261061 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3904. Min Act: -0.0001

Data Index: 1626604 (Python Code)

Max Activating Token Index: 196

Text #5

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3716. Min Act: -0.0001

Data Index: 1490653 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3687. Min Act: -0.0001

Data Index: 254453 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3422. Min Act: -0.0001

Data Index: 1555910 (Python Code)

Max Activating Token Index: 490

Text #8

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3545. Min Act: -0.0001

Data Index: 1512213 (Python Code)

Max Activating Token Index: 340

Text #9

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3500. Min Act: -0.0001

Data Index: 1163450 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3461. Min Act: -0.0001

Data Index: 671992 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3483. Min Act: -0.0001

Data Index: 555238 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3329. Min Act: -0.0001

Data Index: 1165147 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1179468 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3624. Min Act: -0.0001

Data Index: 1373779 (Python Code)

Max Activating Token Index: 701

Text #15

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3548. Min Act: -0.0001

Data Index: 573861 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3360. Min Act: -0.0001

Data Index: 190811 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3404. Min Act: -0.0001

Data Index: 1515179 (Python Code)

Max Activating Token Index: 155

Text #18

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3520. Min Act: -0.0001

Data Index: 1215186 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2954. Min Act: -0.0001

Data Index: 1078671 (C4 (Web Text))

Max Activating Token Index: 770