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

Dataset: The Pile

Neuron 2298 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1048741 (The Pile)

Max Activating Token Index: 426

Text #1

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5647. Min Act: -0.0000

Data Index: 998205 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5139. Min Act: -0.0000

Data Index: 860259 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1046106 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5744. Min Act: -0.0000

Data Index: 763620 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4094. Min Act: -0.0000

Data Index: 163250 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4108. Min Act: -0.0000

Data Index: 832688 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1581211 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4251. Min Act: -0.0000

Data Index: 916053 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1152097 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1751782 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1347987 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.3756. Min Act: -0.0000

Data Index: 623773 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.3850. Min Act: -0.0000

Data Index: 858854 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4057. Min Act: -0.0000

Data Index: 96808 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.3697. Min Act: -0.0000

Data Index: 830232 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.3833. Min Act: -0.0000

Data Index: 888631 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.3813. Min Act: -0.0000

Data Index: 351809 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4004. Min Act: -0.0000

Data Index: 789303 (The Pile)

Max Activating Token Index: 720

Text #19

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1178139 (The Pile)

Max Activating Token Index: 161