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

Dataset: The Pile

Neuron 5043 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: 0.4064. Min Range: -0.4064

Max Act: 0.4064. Min Act: -0.0000

Data Index: 333225 (The Pile)

Max Activating Token Index: 204

Text #1

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1509219 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3137. Min Act: -0.0000

Data Index: 209061 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3063. Min Act: -0.0000

Data Index: 80742 (The Pile)

Max Activating Token Index: 700

Text #4

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3497. Min Act: -0.0000

Data Index: 181286 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1066841 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1095481 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1135754 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3024. Min Act: -0.0000

Data Index: 680654 (The Pile)

Max Activating Token Index: 557

Text #9

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3074. Min Act: -0.0000

Data Index: 30081 (The Pile)

Max Activating Token Index: 711

Text #10

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1524006 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3136. Min Act: -0.0000

Data Index: 596484 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3046. Min Act: -0.0000

Data Index: 948802 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3327. Min Act: -0.0000

Data Index: 116374 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3100. Min Act: -0.0000

Data Index: 949356 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.2785. Min Act: -0.0000

Data Index: 668869 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1290415 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.3058. Min Act: -0.0000

Data Index: 448099 (The Pile)

Max Activating Token Index: 116

Text #18

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.2766. Min Act: -0.0000

Data Index: 194311 (The Pile)

Max Activating Token Index: 909

Text #19

Max Range: 0.4064. Min Range: -0.4064

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1860324 (The Pile)

Max Activating Token Index: 245