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

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

Neuron 4617 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.8860. Min Act: -0.0000

Data Index: 869324 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.7285. Min Act: -0.0000

Data Index: 373883 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.6765. Min Act: -0.0000

Data Index: 997455 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1331563 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.6614. Min Act: -0.0000

Data Index: 960351 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1291537 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.6439. Min Act: -0.0000

Data Index: 777481 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.6019. Min Act: -0.0000

Data Index: 382824 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.5779. Min Act: -0.0000

Data Index: 830630 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1126467 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1262592 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1355377 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1066457 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.4775. Min Act: -0.0000

Data Index: 39860 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1112402 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.4624. Min Act: -0.0000

Data Index: 238016 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.4684. Min Act: -0.0000

Data Index: 113204 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.4735. Min Act: -0.0000

Data Index: 557164 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.4773. Min Act: -0.0000

Data Index: 813482 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.8860. Min Range: -0.8860

Max Act: 0.4906. Min Act: -0.0000

Data Index: 159612 (C4 (Web Text))

Max Activating Token Index: 839