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

Dataset: The Pile

Neuron 710 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.3871. Min Act: -0.0000

Data Index: 389377 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0054. Min Act: -0.0000

Data Index: 258529 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1181062 (The Pile)

Max Activating Token Index: 688

Text #3

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1172116 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0371. Min Act: -0.0000

Data Index: 1124233 (The Pile)

Max Activating Token Index: 231

Text #5

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9312. Min Act: -0.0000

Data Index: 21302 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9890. Min Act: -0.0000

Data Index: 823712 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1608519 (The Pile)

Max Activating Token Index: 208

Text #8

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1315934 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9184. Min Act: -0.0000

Data Index: 985331 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9007. Min Act: -0.0000

Data Index: 697739 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1571584 (The Pile)

Max Activating Token Index: 452

Text #12

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.8934. Min Act: 0.0000

Data Index: 1043842 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.8392. Min Act: 0.0000

Data Index: 108228 (The Pile)

Max Activating Token Index: 162

Text #14

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.8917. Min Act: -0.0000

Data Index: 219086 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.8776. Min Act: -0.0000

Data Index: 925538 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1083942 (The Pile)

Max Activating Token Index: 910

Text #17

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1146919 (The Pile)

Max Activating Token Index: 817

Text #18

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1512755 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1448902 (The Pile)

Max Activating Token Index: 938