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

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

Neuron 4113 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: 1.1261. Min Range: -1.1261

Max Act: 1.1261. Min Act: -0.0000

Data Index: 2638 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.1261. Min Range: -1.1261

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1449614 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 1.1261. Min Range: -1.1261

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1654993 (Python Code)

Max Activating Token Index: 486

Text #3

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1057304 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 1.1261. Min Range: -1.1261

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1538039 (Python Code)

Max Activating Token Index: 705

Text #5

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1436517 (Python Code)

Max Activating Token Index: 601

Text #6

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1455873 (Python Code)

Max Activating Token Index: 656

Text #7

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1568054 (Python Code)

Max Activating Token Index: 761

Text #8

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1533776 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7830. Min Act: -0.0000

Data Index: 953770 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1441427 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1621455 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1449720 (Python Code)

Max Activating Token Index: 325

Text #13

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1285083 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7018. Min Act: -0.0000

Data Index: 214897 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1447676 (Python Code)

Max Activating Token Index: 651

Text #16

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1499104 (Python Code)

Max Activating Token Index: 927

Text #17

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1632153 (Python Code)

Max Activating Token Index: 745

Text #18

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7067. Min Act: -0.0000

Data Index: 295606 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1537393 (Python Code)

Max Activating Token Index: 268