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

Dataset: The Pile

Neuron 4657 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: 0.7489. Min Range: -0.7489

Max Act: 0.7489. Min Act: -0.0000

Data Index: 492636 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.6437. Min Act: -0.0000

Data Index: 1106541 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.6210. Min Act: -0.0000

Data Index: 104106 (The Pile)

Max Activating Token Index: 967

Text #3

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.6156. Min Act: -0.0000

Data Index: 284668 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5534. Min Act: -0.0000

Data Index: 169223 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5988. Min Act: -0.0000

Data Index: 258382 (The Pile)

Max Activating Token Index: 128

Text #6

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1113270 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1144947 (The Pile)

Max Activating Token Index: 577

Text #8

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5745. Min Act: -0.0000

Data Index: 7706 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1149829 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1885794 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5254. Min Act: -0.0000

Data Index: 866978 (The Pile)

Max Activating Token Index: 352

Text #12

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5341. Min Act: -0.0000

Data Index: 485262 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1143094 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5497. Min Act: -0.0000

Data Index: 461600 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1482629 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5096. Min Act: -0.0000

Data Index: 960168 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1334571 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1522042 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1438178 (The Pile)

Max Activating Token Index: 535