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

Dataset: The Pile

Neuron 670 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: 1.1195. Min Range: -1.1195

Max Act: 1.1195. Min Act: -0.0000

Data Index: 424987 (The Pile)

Max Activating Token Index: 727

Text #1

Max Range: 1.1195. Min Range: -1.1195

Max Act: 1.0241. Min Act: -0.0000

Data Index: 266190 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8811. Min Act: -0.0000

Data Index: 845541 (The Pile)

Max Activating Token Index: 562

Text #3

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8292. Min Act: -0.0000

Data Index: 161442 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.7463. Min Act: 0.0000

Data Index: 642620 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1019924 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.9060. Min Act: -0.0000

Data Index: 61053 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.7716. Min Act: -0.0000

Data Index: 242556 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.7325. Min Act: -0.0000

Data Index: 543519 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.6524. Min Act: -0.0000

Data Index: 257331 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1550900 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1869697 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.6107. Min Act: -0.0000

Data Index: 626381 (The Pile)

Max Activating Token Index: 631

Text #13

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.7069. Min Act: -0.0000

Data Index: 514613 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1539210 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1224260 (The Pile)

Max Activating Token Index: 119

Text #16

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1973302 (The Pile)

Max Activating Token Index: 703

Text #17

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1675295 (The Pile)

Max Activating Token Index: 414

Text #18

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1572296 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.6596. Min Act: 0.0000

Data Index: 1976078 (The Pile)

Max Activating Token Index: 155