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

Dataset: The Pile

Neuron 157 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4506. Min Act: -0.0000

Data Index: 1221477 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.5694. Min Act: -0.0000

Data Index: 562924 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4982. Min Act: -0.0000

Data Index: 176456 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4071. Min Act: -0.0000

Data Index: 285047 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1678784 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4593. Min Act: -0.0000

Data Index: 244632 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4060. Min Act: -0.0000

Data Index: 1223705 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3683. Min Act: -0.0000

Data Index: 1498338 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3992. Min Act: -0.0000

Data Index: 884088 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1037526 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1073375 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1912109 (The Pile)

Max Activating Token Index: 357

Text #12

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2871. Min Act: -0.0000

Data Index: 723207 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1158347 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2846. Min Act: -0.0000

Data Index: 1172479 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3913. Min Act: -0.0000

Data Index: 1697222 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4018. Min Act: -0.0000

Data Index: 1565120 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1801358 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2056. Min Act: -0.0000

Data Index: 1212685 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3001. Min Act: -0.0000

Data Index: 459098 (The Pile)

Max Activating Token Index: 332