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

Dataset: The Pile

Neuron 3208 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1619065 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4884. Min Act: -0.0000

Data Index: 893172 (The Pile)

Max Activating Token Index: 375

Text #2

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4683. Min Act: -0.0000

Data Index: 505874 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1069552 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1267116 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4350. Min Act: -0.0000

Data Index: 339371 (The Pile)

Max Activating Token Index: 104

Text #6

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4253. Min Act: -0.0000

Data Index: 612238 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4652. Min Act: -0.0000

Data Index: 582343 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4599. Min Act: -0.0000

Data Index: 794345 (The Pile)

Max Activating Token Index: 323

Text #9

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4503. Min Act: -0.0000

Data Index: 712265 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1303214 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4182. Min Act: -0.0000

Data Index: 308763 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4427. Min Act: -0.0000

Data Index: 746819 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4455. Min Act: -0.0000

Data Index: 900705 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1664924 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1148570 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4535. Min Act: -0.0000

Data Index: 480540 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1073190 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1180615 (The Pile)

Max Activating Token Index: 231

Text #19

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4000. Min Act: -0.0000

Data Index: 622604 (The Pile)

Max Activating Token Index: 897