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

Dataset: The Pile

Neuron 1498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6345. Min Act: 0.0000

Data Index: 224123 (The Pile)

Max Activating Token Index: 838

Text #1

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6419. Min Act: -0.0000

Data Index: 658518 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1323021 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1138470 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4628. Min Act: 0.0000

Data Index: 1457146 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1605212 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1084323 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4408. Min Act: -0.0000

Data Index: 288615 (The Pile)

Max Activating Token Index: 218

Text #8

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4219. Min Act: -0.0001

Data Index: 1048731 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1044405 (The Pile)

Max Activating Token Index: 213

Text #10

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4139. Min Act: -0.0001

Data Index: 208041 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4239. Min Act: -0.0000

Data Index: 799489 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4682. Min Act: -0.0001

Data Index: 738957 (The Pile)

Max Activating Token Index: 193

Text #13

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4362. Min Act: 0.0000

Data Index: 147413 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4131. Min Act: -0.0000

Data Index: 984907 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1010224 (The Pile)

Max Activating Token Index: 396

Text #16

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1852422 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4184. Min Act: 0.0000

Data Index: 1620306 (The Pile)

Max Activating Token Index: 666

Text #18

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.3802. Min Act: 0.0000

Data Index: 1430494 (The Pile)

Max Activating Token Index: 369

Text #19

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.3836. Min Act: -0.0000

Data Index: 374748 (The Pile)

Max Activating Token Index: 232