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

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

Neuron 138 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: 1.3363. Min Range: -1.3363

Max Act: 1.3363. Min Act: -0.0000

Data Index: 1616620 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2468. Min Act: -0.0000

Data Index: 1642625 (Python Code)

Max Activating Token Index: 764

Text #2

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.0766. Min Act: -0.0000

Data Index: 637717 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1587500 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.0353. Min Act: -0.0000

Data Index: 785259 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1066569 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1413416 (Python Code)

Max Activating Token Index: 532

Text #7

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1337814 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1480431 (Python Code)

Max Activating Token Index: 527

Text #9

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1639415 (Python Code)

Max Activating Token Index: 338

Text #10

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9138. Min Act: -0.0000

Data Index: 644913 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.8507. Min Act: -0.0000

Data Index: 402797 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9604. Min Act: -0.0000

Data Index: 691163 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1606490 (Python Code)

Max Activating Token Index: 740

Text #14

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1491442 (Python Code)

Max Activating Token Index: 249

Text #15

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1361562 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1496910 (Python Code)

Max Activating Token Index: 866

Text #17

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1360804 (Python Code)

Max Activating Token Index: 209

Text #18

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1567062 (Python Code)

Max Activating Token Index: 947

Text #19

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1537707 (Python Code)

Max Activating Token Index: 922