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

Dataset: The Pile

Neuron 545 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1367493 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6282. Min Act: -0.0000

Data Index: 742144 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6784. Min Act: -0.0000

Data Index: 483583 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6967. Min Act: -0.0000

Data Index: 30082 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6351. Min Act: -0.0000

Data Index: 19803 (The Pile)

Max Activating Token Index: 964

Text #5

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1528902 (The Pile)

Max Activating Token Index: 672

Text #6

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6325. Min Act: -0.0000

Data Index: 790270 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6323. Min Act: -0.0000

Data Index: 337409 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1660197 (The Pile)

Max Activating Token Index: 506

Text #9

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1941817 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6791. Min Act: -0.0000

Data Index: 666391 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5785. Min Act: -0.0000

Data Index: 711321 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6275. Min Act: -0.0000

Data Index: 849438 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1138984 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5227. Min Act: -0.0000

Data Index: 890500 (The Pile)

Max Activating Token Index: 44

Text #15

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5961. Min Act: -0.0000

Data Index: 91012 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1413269 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5576. Min Act: -0.0000

Data Index: 818735 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5729. Min Act: -0.0000

Data Index: 530789 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1292761 (The Pile)

Max Activating Token Index: 54