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

Dataset: The Pile

Neuron 972 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: 0.4112. Min Range: -0.4112

Max Act: 0.4112. Min Act: 0.0000

Data Index: 719325 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1408142 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3911. Min Act: -0.0000

Data Index: 707744 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3694. Min Act: 0.0000

Data Index: 1854492 (The Pile)

Max Activating Token Index: 812

Text #4

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1406526 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1360049 (The Pile)

Max Activating Token Index: 480

Text #6

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1519072 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1530442 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3479. Min Act: -0.0000

Data Index: 525791 (The Pile)

Max Activating Token Index: 416

Text #9

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3683. Min Act: -0.0000

Data Index: 64240 (The Pile)

Max Activating Token Index: 432

Text #10

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3531. Min Act: -0.0000

Data Index: 876399 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3571. Min Act: -0.0000

Data Index: 471043 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1061851 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3529. Min Act: -0.0000

Data Index: 391430 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3266. Min Act: -0.0000

Data Index: 537690 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1907964 (The Pile)

Max Activating Token Index: 593

Text #16

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3552. Min Act: -0.0000

Data Index: 320531 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1214061 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3473. Min Act: -0.0000

Data Index: 792030 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3256. Min Act: -0.0000

Data Index: 197487 (The Pile)

Max Activating Token Index: 253