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

Dataset: The Pile

Neuron 1138 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0574. Min Range: -1.0574

Max Act: 1.0574. Min Act: -0.0000

Data Index: 218665 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8816. Min Act: -0.0000

Data Index: 13224 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1548962 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8779. Min Act: -0.0000

Data Index: 403840 (The Pile)

Max Activating Token Index: 191

Text #4

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8627. Min Act: -0.0000

Data Index: 605963 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8560. Min Act: -0.0000

Data Index: 414911 (The Pile)

Max Activating Token Index: 656

Text #6

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1168416 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8456. Min Act: -0.0000

Data Index: 686645 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1076763 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1198678 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8249. Min Act: -0.0000

Data Index: 745224 (The Pile)

Max Activating Token Index: 584

Text #11

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8272. Min Act: -0.0000

Data Index: 819254 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1758421 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8176. Min Act: -0.0000

Data Index: 879352 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1375126 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8267. Min Act: -0.0000

Data Index: 711994 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7349. Min Act: -0.0000

Data Index: 34412 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1048362 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1576118 (The Pile)

Max Activating Token Index: 522

Text #19

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7647. Min Act: -0.0000

Data Index: 842163 (The Pile)

Max Activating Token Index: 553