Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4605 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7930. Min Act: -0.0000

Data Index: 271539 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7803. Min Act: -0.0000

Data Index: 870277 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.8080. Min Act: -0.0000

Data Index: 554416 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1912940 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1295648 (The Pile)

Max Activating Token Index: 631

Text #5

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7460. Min Act: -0.0000

Data Index: 924417 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1920436 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1250295 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1794694 (The Pile)

Max Activating Token Index: 996

Text #9

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7066. Min Act: -0.0000

Data Index: 443702 (The Pile)

Max Activating Token Index: 465

Text #10

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6576. Min Act: -0.0000

Data Index: 828870 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1846380 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1281933 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6670. Min Act: -0.0000

Data Index: 661034 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6210. Min Act: -0.0000

Data Index: 931573 (The Pile)

Max Activating Token Index: 232

Text #15

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1224479 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1942727 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5965. Min Act: -0.0000

Data Index: 921071 (The Pile)

Max Activating Token Index: 197

Text #18

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5722. Min Act: -0.0000

Data Index: 526886 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1338199 (The Pile)

Max Activating Token Index: 957