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

Dataset: The Pile

Neuron 3009 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1397213 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7672. Min Act: 0.0000

Data Index: 1085353 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8200. Min Act: -0.0000

Data Index: 139000 (The Pile)

Max Activating Token Index: 131

Text #3

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8748. Min Act: -0.0000

Data Index: 1579277 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.9327. Min Act: 0.0000

Data Index: 1132248 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7487. Min Act: 0.0000

Data Index: 932629 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8091. Min Act: -0.0000

Data Index: 430943 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7207. Min Act: -0.0000

Data Index: 291528 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1444984 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7550. Min Act: -0.0000

Data Index: 439965 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7809. Min Act: -0.0000

Data Index: 345375 (The Pile)

Max Activating Token Index: 841

Text #11

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8182. Min Act: -0.0000

Data Index: 255712 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6952. Min Act: -0.0000

Data Index: 552123 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7882. Min Act: -0.0000

Data Index: 453667 (The Pile)

Max Activating Token Index: 455

Text #14

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7871. Min Act: 0.0000

Data Index: 1378414 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7180. Min Act: -0.0000

Data Index: 519665 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1035243 (The Pile)

Max Activating Token Index: 854

Text #17

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1175849 (The Pile)

Max Activating Token Index: 852

Text #18

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1460402 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7727. Min Act: -0.0000

Data Index: 792581 (The Pile)

Max Activating Token Index: 692