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

Dataset: The Pile

Neuron 3972 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3157. Min Act: -0.0000

Data Index: 804700 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1095269 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1397626 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2807. Min Act: -0.0000

Data Index: 205905 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1706665 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1112553 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2758. Min Act: -0.0000

Data Index: 515289 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1438407 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2737. Min Act: -0.0000

Data Index: 184855 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1965565 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2520. Min Act: -0.0000

Data Index: 112103 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2699. Min Act: -0.0000

Data Index: 713138 (The Pile)

Max Activating Token Index: 778

Text #12

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1456705 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1635855 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2549. Min Act: -0.0000

Data Index: 816897 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2478. Min Act: -0.0000

Data Index: 884755 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1129135 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2608. Min Act: -0.0000

Data Index: 499694 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2089. Min Act: -0.0000

Data Index: 303881 (The Pile)

Max Activating Token Index: 129

Text #19

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2381. Min Act: -0.0000

Data Index: 355792 (The Pile)

Max Activating Token Index: 651