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

Dataset: The Pile

Neuron 2613 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1811097 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1055500 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3794. Min Act: -0.0000

Data Index: 561549 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3907. Min Act: -0.0000

Data Index: 403257 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1694373 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4045. Min Act: -0.0000

Data Index: 589111 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4326. Min Act: -0.0000

Data Index: 179507 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4036. Min Act: -0.0000

Data Index: 602723 (The Pile)

Max Activating Token Index: 885

Text #8

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4212. Min Act: -0.0000

Data Index: 594521 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3484. Min Act: -0.0000

Data Index: 91686 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1101055 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1761679 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1049275 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1875208 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1394635 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1674394 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3914. Min Act: -0.0000

Data Index: 982238 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1638126 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1833098 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3757. Min Act: -0.0000

Data Index: 984038 (The Pile)

Max Activating Token Index: 309