Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3872 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1015. Min Range: -1.1015

Max Act: 1.1015. Min Act: -0.0000

Data Index: 848480 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9971. Min Act: -0.0000

Data Index: 365414 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9986. Min Act: -0.0000

Data Index: 1339036 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8851. Min Act: -0.0000

Data Index: 987580 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9876. Min Act: -0.0000

Data Index: 744 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8985. Min Act: -0.0000

Data Index: 728442 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8884. Min Act: -0.0000

Data Index: 736432 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1018010 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1301557 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8282. Min Act: -0.0000

Data Index: 403203 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8571. Min Act: -0.0000

Data Index: 128814 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1067201 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8179. Min Act: -0.0000

Data Index: 652059 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8456. Min Act: -0.0000

Data Index: 464973 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8463. Min Act: -0.0000

Data Index: 17706 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1268144 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7940. Min Act: -0.0000

Data Index: 395399 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7850. Min Act: 0.0000

Data Index: 100971 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7621. Min Act: -0.0000

Data Index: 272461 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7825. Min Act: 0.0000

Data Index: 692402 (C4 (Web Text))

Max Activating Token Index: 920