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

Dataset: The Pile

Neuron 3892 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: 5.2188. Min Range: -5.2188

Max Act: 5.2049. Min Act: -0.0000

Data Index: 1711379 (The Pile)

Max Activating Token Index: 285

Text #1

Max Range: 5.2188. Min Range: -5.2188

Max Act: 5.1923. Min Act: -0.0000

Data Index: 1905758 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.9813. Min Act: -0.0000

Data Index: 1144951 (The Pile)

Max Activating Token Index: 522

Text #3

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.9489. Min Act: -0.0000

Data Index: 757149 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 5.2188. Min Range: -5.2188

Max Act: 5.0974. Min Act: -0.0000

Data Index: 1126798 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.9147. Min Act: -0.0000

Data Index: 1132441 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 5.2188. Min Range: -5.2188

Max Act: 5.2188. Min Act: -0.0000

Data Index: 1534600 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.7936. Min Act: -0.0000

Data Index: 37925 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.7300. Min Act: -0.0000

Data Index: 1329924 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.7083. Min Act: -0.0000

Data Index: 1175013 (The Pile)

Max Activating Token Index: 734

Text #10

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.6937. Min Act: -0.0000

Data Index: 329379 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.7273. Min Act: -0.0000

Data Index: 1605004 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.4891. Min Act: -0.0000

Data Index: 215088 (The Pile)

Max Activating Token Index: 67

Text #13

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.6523. Min Act: -0.0000

Data Index: 1793881 (The Pile)

Max Activating Token Index: 246

Text #14

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.8171. Min Act: -0.0000

Data Index: 186626 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.6283. Min Act: -0.0000

Data Index: 1398012 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.9485. Min Act: -0.0000

Data Index: 1494908 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.7694. Min Act: -0.0000

Data Index: 1013569 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.7577. Min Act: -0.0000

Data Index: 568117 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 5.2188. Min Range: -5.2188

Max Act: 4.7517. Min Act: -0.0000

Data Index: 1189616 (The Pile)

Max Activating Token Index: 273