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

Dataset: The Pile

Neuron 1377 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: 0.6199. Min Range: -0.6199

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1945867 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1265715 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1171090 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.6139. Min Act: -0.0000

Data Index: 41694 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1414866 (The Pile)

Max Activating Token Index: 357

Text #5

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1078935 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1374269 (The Pile)

Max Activating Token Index: 910

Text #7

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1305241 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1133674 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1708908 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5308. Min Act: -0.0000

Data Index: 423284 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5143. Min Act: -0.0000

Data Index: 645125 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5614. Min Act: -0.0000

Data Index: 420158 (The Pile)

Max Activating Token Index: 653

Text #13

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1528920 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1843828 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5601. Min Act: -0.0000

Data Index: 522103 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5248. Min Act: -0.0000

Data Index: 359327 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5146. Min Act: -0.0000

Data Index: 237682 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1255326 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1536098 (The Pile)

Max Activating Token Index: 423