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

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

Neuron 1264 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8660. Min Act: -0.0002

Data Index: 579049 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.9100. Min Act: -0.0002

Data Index: 148573 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8431. Min Act: -0.0002

Data Index: 1208529 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8629. Min Act: -0.0002

Data Index: 1013102 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8418. Min Act: -0.0002

Data Index: 267748 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7971. Min Act: -0.0002

Data Index: 722842 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7976. Min Act: -0.0002

Data Index: 487001 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7783. Min Act: -0.0002

Data Index: 140979 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7734. Min Act: -0.0002

Data Index: 197625 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7389. Min Act: -0.0002

Data Index: 492489 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7325. Min Act: -0.0002

Data Index: 927280 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7626. Min Act: -0.0002

Data Index: 40767 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7663. Min Act: -0.0002

Data Index: 108601 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7324. Min Act: -0.0002

Data Index: 1096101 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7433. Min Act: -0.0002

Data Index: 983754 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7411. Min Act: -0.0002

Data Index: 345159 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6971. Min Act: -0.0002

Data Index: 1121970 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6966. Min Act: -0.0002

Data Index: 2411 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7202. Min Act: -0.0002

Data Index: 1218975 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6901. Min Act: -0.0002

Data Index: 714030 (C4 (Web Text))

Max Activating Token Index: 592