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

Dataset: The Pile

Neuron 767 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: 1.8749. Min Range: -1.8749

Max Act: 1.8749. Min Act: -0.0000

Data Index: 191416 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.5955. Min Act: -0.0000

Data Index: 1276555 (The Pile)

Max Activating Token Index: 332

Text #2

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.5488. Min Act: -0.0000

Data Index: 1493695 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.5975. Min Act: -0.0000

Data Index: 312428 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.4490. Min Act: -0.0000

Data Index: 50954 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.4870. Min Act: -0.0000

Data Index: 1467346 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.3491. Min Act: -0.0000

Data Index: 474612 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.4195. Min Act: -0.0000

Data Index: 1243277 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.3394. Min Act: -0.0000

Data Index: 356881 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.4561. Min Act: -0.0000

Data Index: 882040 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.3021. Min Act: -0.0000

Data Index: 1461754 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.4094. Min Act: -0.0000

Data Index: 876612 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.3663. Min Act: -0.0000

Data Index: 96400 (The Pile)

Max Activating Token Index: 426

Text #13

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1584041 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.3810. Min Act: -0.0000

Data Index: 1002092 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1304281 (The Pile)

Max Activating Token Index: 516

Text #16

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.3205. Min Act: -0.0000

Data Index: 1608793 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.3198. Min Act: -0.0000

Data Index: 214692 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.2755. Min Act: -0.0000

Data Index: 1130956 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.3094. Min Act: -0.0000

Data Index: 265574 (The Pile)

Max Activating Token Index: 520