Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1130 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2927. Min Act: -0.0003

Data Index: 1416571 (Python Code)

Max Activating Token Index: 843

Text #1

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3081. Min Act: -0.0003

Data Index: 144718 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3009. Min Act: -0.0002

Data Index: 1374364 (Python Code)

Max Activating Token Index: 465

Text #3

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3035. Min Act: -0.0003

Data Index: 1375457 (Python Code)

Max Activating Token Index: 808

Text #4

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3017. Min Act: -0.0002

Data Index: 1447593 (Python Code)

Max Activating Token Index: 735

Text #5

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2896. Min Act: -0.0003

Data Index: 1517072 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2962. Min Act: -0.0003

Data Index: 1390952 (Python Code)

Max Activating Token Index: 417

Text #7

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2900. Min Act: -0.0003

Data Index: 1511044 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2749. Min Act: -0.0003

Data Index: 1437806 (Python Code)

Max Activating Token Index: 704

Text #9

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2596. Min Act: -0.0003

Data Index: 1448292 (Python Code)

Max Activating Token Index: 624

Text #10

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2810. Min Act: -0.0003

Data Index: 1543586 (Python Code)

Max Activating Token Index: 749

Text #11

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2666. Min Act: -0.0004

Data Index: 1563611 (Python Code)

Max Activating Token Index: 786

Text #12

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2717. Min Act: -0.0003

Data Index: 1508439 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2649. Min Act: -0.0003

Data Index: 1428876 (Python Code)

Max Activating Token Index: 726

Text #14

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2808. Min Act: -0.0003

Data Index: 1539228 (Python Code)

Max Activating Token Index: 66

Text #15

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2507. Min Act: -0.0003

Data Index: 1562378 (Python Code)

Max Activating Token Index: 700

Text #16

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2723. Min Act: -0.0003

Data Index: 1412830 (Python Code)

Max Activating Token Index: 825

Text #17

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2572. Min Act: -0.0003

Data Index: 1519409 (Python Code)

Max Activating Token Index: 807

Text #18

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2601. Min Act: -0.0002

Data Index: 1576732 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2668. Min Act: -0.0003

Data Index: 931782 (C4 (Web Text))

Max Activating Token Index: 763