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

Dataset: The Pile

Neuron 642 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: 0.4107. Min Range: -0.4107

Max Act: 0.4095. Min Act: -0.0000

Data Index: 213627 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.4107. Min Act: -0.0000

Data Index: 171726 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3762. Min Act: -0.0000

Data Index: 154520 (The Pile)

Max Activating Token Index: 914

Text #3

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1972662 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1782680 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1015964 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1416180 (The Pile)

Max Activating Token Index: 294

Text #7

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3385. Min Act: -0.0000

Data Index: 754037 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1224528 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3205. Min Act: -0.0000

Data Index: 153169 (The Pile)

Max Activating Token Index: 26

Text #10

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1200256 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1363190 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2961. Min Act: -0.0000

Data Index: 325153 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1800522 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2968. Min Act: -0.0000

Data Index: 774838 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1880360 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2761. Min Act: -0.0000

Data Index: 254266 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2700. Min Act: -0.0000

Data Index: 337582 (The Pile)

Max Activating Token Index: 910

Text #18

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2976. Min Act: -0.0000

Data Index: 489391 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3004. Min Act: -0.0000

Data Index: 838775 (The Pile)

Max Activating Token Index: 657