Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3535 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1514014 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1327144 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3079. Min Act: -0.0000

Data Index: 744782 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3159. Min Act: -0.0000

Data Index: 10842 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3301. Min Act: -0.0000

Data Index: 624562 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1082546 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1365708 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1041518 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2904. Min Act: 0.0000

Data Index: 1383888 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1204221 (The Pile)

Max Activating Token Index: 314

Text #10

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2801. Min Act: -0.0000

Data Index: 765658 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1411228 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1325655 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2810. Min Act: -0.0000

Data Index: 93104 (The Pile)

Max Activating Token Index: 985

Text #14

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2826. Min Act: -0.0000

Data Index: 75079 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2806. Min Act: -0.0000

Data Index: 532093 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1091240 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1132962 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1302927 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1569368 (The Pile)

Max Activating Token Index: 584