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

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

Neuron 1570 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: 4.3506. Min Range: -4.3506

Max Act: 4.3506. Min Act: -0.0000

Data Index: 242708 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 4.3506. Min Range: -4.3506

Max Act: 3.5784. Min Act: -0.0000

Data Index: 1355595 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 4.3506. Min Range: -4.3506

Max Act: 3.5631. Min Act: 0.0000

Data Index: 861180 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 4.3506. Min Range: -4.3506

Max Act: 3.3576. Min Act: -0.0000

Data Index: 1075784 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 4.3506. Min Range: -4.3506

Max Act: 3.4050. Min Act: -0.0000

Data Index: 567796 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 4.3506. Min Range: -4.3506

Max Act: 3.2436. Min Act: -0.0000

Data Index: 361162 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 4.3506. Min Range: -4.3506

Max Act: 3.2654. Min Act: -0.0000

Data Index: 1172253 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 4.3506. Min Range: -4.3506

Max Act: 3.2465. Min Act: -0.0000

Data Index: 511722 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 4.3506. Min Range: -4.3506

Max Act: 3.2557. Min Act: -0.0000

Data Index: 458288 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 4.3506. Min Range: -4.3506

Max Act: 3.0322. Min Act: -0.0000

Data Index: 330681 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 4.3506. Min Range: -4.3506

Max Act: 2.9558. Min Act: 0.0000

Data Index: 832086 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 4.3506. Min Range: -4.3506

Max Act: 2.9326. Min Act: -0.0000

Data Index: 481532 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 4.3506. Min Range: -4.3506

Max Act: 2.6456. Min Act: -0.0000

Data Index: 877490 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 4.3506. Min Range: -4.3506

Max Act: 2.7552. Min Act: -0.0000

Data Index: 1289406 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 4.3506. Min Range: -4.3506

Max Act: 2.8951. Min Act: -0.0000

Data Index: 869729 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 4.3506. Min Range: -4.3506

Max Act: 2.8076. Min Act: -0.0000

Data Index: 1201999 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 4.3506. Min Range: -4.3506

Max Act: 2.6342. Min Act: -0.0000

Data Index: 194442 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 4.3506. Min Range: -4.3506

Max Act: 2.7105. Min Act: -0.0000

Data Index: 1073545 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 4.3506. Min Range: -4.3506

Max Act: 2.8487. Min Act: -0.0000

Data Index: 473545 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 4.3506. Min Range: -4.3506

Max Act: 2.4945. Min Act: -0.0000

Data Index: 166950 (C4 (Web Text))

Max Activating Token Index: 221