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

Dataset: The Pile

Neuron 2659 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.2740. Min Act: -0.0000

Data Index: 695545 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1449656 (The Pile)

Max Activating Token Index: 226

Text #2

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1099412 (The Pile)

Max Activating Token Index: 883

Text #3

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.1387. Min Act: -0.0000

Data Index: 966650 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.1329. Min Act: -0.0000

Data Index: 805305 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.0643. Min Act: -0.0000

Data Index: 1811072 (The Pile)

Max Activating Token Index: 122

Text #6

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1479497 (The Pile)

Max Activating Token Index: 797

Text #7

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9809. Min Act: -0.0000

Data Index: 922813 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1111151 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1463237 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9635. Min Act: -0.0000

Data Index: 683784 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1195085 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1074755 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1900749 (The Pile)

Max Activating Token Index: 909

Text #14

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1499294 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1118652 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8870. Min Act: -0.0000

Data Index: 674813 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8435. Min Act: -0.0000

Data Index: 436969 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1151019 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1323946 (The Pile)

Max Activating Token Index: 218