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

Dataset: The Pile

Neuron 3466 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: 0.5948. Min Range: -0.5948

Max Act: 0.5948. Min Act: -0.0000

Data Index: 419850 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1950033 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1441392 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.5396. Min Act: -0.0000

Data Index: 967434 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.5253. Min Act: -0.0000

Data Index: 433409 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1651410 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1834117 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1015522 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1719165 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4737. Min Act: -0.0000

Data Index: 625875 (The Pile)

Max Activating Token Index: 240

Text #10

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1047297 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1786885 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1371372 (The Pile)

Max Activating Token Index: 710

Text #13

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4836. Min Act: -0.0000

Data Index: 129205 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4670. Min Act: -0.0000

Data Index: 628305 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4819. Min Act: -0.0000

Data Index: 664213 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.5041. Min Act: -0.0000

Data Index: 639177 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4723. Min Act: -0.0000

Data Index: 66362 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4885. Min Act: -0.0000

Data Index: 355220 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 0.5948. Min Range: -0.5948

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1629940 (The Pile)

Max Activating Token Index: 114