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

Dataset: The Pile

Neuron 376 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: 3.1952. Min Range: -3.1952

Max Act: 3.1952. Min Act: -0.0000

Data Index: 1196308 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.9553. Min Act: -0.0000

Data Index: 1423412 (The Pile)

Max Activating Token Index: 695

Text #2

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8058. Min Act: -0.0000

Data Index: 542069 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.7785. Min Act: -0.0000

Data Index: 233696 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8372. Min Act: -0.0000

Data Index: 1323302 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8086. Min Act: -0.0000

Data Index: 859673 (The Pile)

Max Activating Token Index: 716

Text #6

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.7940. Min Act: -0.0000

Data Index: 63186 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.6547. Min Act: -0.0000

Data Index: 401683 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.4071. Min Act: -0.0000

Data Index: 1817870 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.7876. Min Act: -0.0000

Data Index: 1250580 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8654. Min Act: -0.0000

Data Index: 227049 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8817. Min Act: -0.0000

Data Index: 1934667 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.7042. Min Act: -0.0000

Data Index: 393187 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.9790. Min Act: -0.0000

Data Index: 736054 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1116. Min Act: -0.0000

Data Index: 1566416 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.3911. Min Act: -0.0000

Data Index: 1971968 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.6738. Min Act: -0.0000

Data Index: 79984 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.6592. Min Act: -0.0000

Data Index: 911996 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.4914. Min Act: -0.0000

Data Index: 389913 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.5264. Min Act: -0.0000

Data Index: 693758 (The Pile)

Max Activating Token Index: 114