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

Dataset: The Pile

Neuron 4061 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: 0.3644. Min Range: -0.3644

Max Act: 0.3644. Min Act: 0.0000

Data Index: 587606 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3541. Min Act: -0.0000

Data Index: 454357 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3475. Min Act: 0.0000

Data Index: 735558 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1656306 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1727274 (The Pile)

Max Activating Token Index: 463

Text #5

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3218. Min Act: -0.0000

Data Index: 93572 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3371. Min Act: 0.0000

Data Index: 1805892 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1679782 (The Pile)

Max Activating Token Index: 231

Text #8

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1301298 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1599225 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3207. Min Act: -0.0000

Data Index: 166098 (The Pile)

Max Activating Token Index: 209

Text #11

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1177234 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2967. Min Act: 0.0000

Data Index: 1205910 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1034674 (The Pile)

Max Activating Token Index: 658

Text #14

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2903. Min Act: 0.0001

Data Index: 990941 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2879. Min Act: -0.0000

Data Index: 427527 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2861. Min Act: -0.0000

Data Index: 359179 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1306741 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1619506 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2973. Min Act: -0.0000

Data Index: 891447 (The Pile)

Max Activating Token Index: 825