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

Dataset: The Pile

Neuron 2614 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3975. Min Act: -0.0000

Data Index: 724329 (The Pile)

Max Activating Token Index: 149

Text #1

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3787. Min Act: 0.0000

Data Index: 406856 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1024701 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1989045 (The Pile)

Max Activating Token Index: 390

Text #4

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3536. Min Act: -0.0000

Data Index: 422273 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1771102 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3154. Min Act: -0.0000

Data Index: 753997 (The Pile)

Max Activating Token Index: 38

Text #7

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2810. Min Act: -0.0000

Data Index: 708320 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2949. Min Act: 0.0000

Data Index: 1615472 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2866. Min Act: -0.0000

Data Index: 878582 (The Pile)

Max Activating Token Index: 124

Text #10

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1951877 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1386917 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2785. Min Act: 0.0000

Data Index: 317286 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1964273 (The Pile)

Max Activating Token Index: 513

Text #14

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2399. Min Act: -0.0000

Data Index: 626901 (The Pile)

Max Activating Token Index: 680

Text #15

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1575816 (The Pile)

Max Activating Token Index: 40

Text #16

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1302202 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2559. Min Act: 0.0001

Data Index: 478720 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1329745 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2539. Min Act: -0.0000

Data Index: 961622 (The Pile)

Max Activating Token Index: 190