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

Dataset: The Pile

Neuron 3799 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1636845 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1799957 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1494846 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1968983 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1782361 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4083. Min Act: -0.0000

Data Index: 650794 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1304360 (The Pile)

Max Activating Token Index: 231

Text #7

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3708. Min Act: -0.0000

Data Index: 253059 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3628. Min Act: 0.0000

Data Index: 173451 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3421. Min Act: -0.0000

Data Index: 748156 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3655. Min Act: -0.0000

Data Index: 446623 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1421509 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1550563 (The Pile)

Max Activating Token Index: 261

Text #13

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1361974 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3321. Min Act: -0.0000

Data Index: 172004 (The Pile)

Max Activating Token Index: 676

Text #15

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3283. Min Act: -0.0000

Data Index: 139665 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1478466 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1729419 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1590632 (The Pile)

Max Activating Token Index: 555

Text #19

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1779935 (The Pile)

Max Activating Token Index: 742