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

Dataset: The Pile

Neuron 2962 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: 0.9670. Min Range: -0.9670

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1488882 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1801813 (The Pile)

Max Activating Token Index: 333

Text #2

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7706. Min Act: -0.0000

Data Index: 830009 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1991695 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7443. Min Act: -0.0000

Data Index: 862621 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7481. Min Act: -0.0000

Data Index: 128324 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1702486 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1671518 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6980. Min Act: -0.0000

Data Index: 611569 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6815. Min Act: -0.0000

Data Index: 359436 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6554. Min Act: -0.0000

Data Index: 33081 (The Pile)

Max Activating Token Index: 227

Text #11

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1161447 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6258. Min Act: -0.0000

Data Index: 897082 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1369772 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1496830 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1076833 (The Pile)

Max Activating Token Index: 17

Text #16

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1399407 (The Pile)

Max Activating Token Index: 276

Text #17

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1047777 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5986. Min Act: -0.0000

Data Index: 4549 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1088164 (The Pile)

Max Activating Token Index: 562