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

Dataset: The Pile

Neuron 3666 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: 3.3662. Min Range: -3.3662

Max Act: 3.3330. Min Act: -0.0000

Data Index: 1651303 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.3662. Min Act: -0.0000

Data Index: 343767 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.9711. Min Act: -0.0000

Data Index: 1921845 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.9190. Min Act: -0.0000

Data Index: 1069968 (The Pile)

Max Activating Token Index: 514

Text #4

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.9000. Min Act: -0.0000

Data Index: 1809400 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.8336. Min Act: -0.0000

Data Index: 1990988 (The Pile)

Max Activating Token Index: 307

Text #6

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.7987. Min Act: -0.0000

Data Index: 685916 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.7226. Min Act: -0.0000

Data Index: 1807014 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.7555. Min Act: -0.0000

Data Index: 15846 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.5803. Min Act: -0.0000

Data Index: 1259987 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.8968. Min Act: -0.0000

Data Index: 1145492 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.6895. Min Act: -0.0000

Data Index: 1769711 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.0892. Min Act: -0.0000

Data Index: 1589679 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 3.3662. Min Range: -3.3662

Max Act: 2.1331. Min Act: -0.0000

Data Index: 384878 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 3.3662. Min Range: -3.3662

Max Act: 1.9398. Min Act: -0.0000

Data Index: 1121677 (The Pile)

Max Activating Token Index: 760

Text #15

Max Range: 3.3662. Min Range: -3.3662

Max Act: 1.6215. Min Act: -0.0000

Data Index: 1027632 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 3.3662. Min Range: -3.3662

Max Act: 1.6107. Min Act: -0.0000

Data Index: 886490 (The Pile)

Max Activating Token Index: 703

Text #17

Max Range: 3.3662. Min Range: -3.3662

Max Act: 1.5956. Min Act: -0.0000

Data Index: 11308 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 3.3662. Min Range: -3.3662

Max Act: 1.5312. Min Act: -0.0000

Data Index: 1796902 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 3.3662. Min Range: -3.3662

Max Act: 1.5169. Min Act: -0.0000

Data Index: 1724680 (The Pile)

Max Activating Token Index: 726