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

Dataset: The Pile

Neuron 1121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1664124 (The Pile)

Max Activating Token Index: 694

Text #1

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.9384. Min Act: -0.0000

Data Index: 800561 (The Pile)

Max Activating Token Index: 604

Text #2

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1066672 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1749023 (The Pile)

Max Activating Token Index: 72

Text #4

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8443. Min Act: -0.0000

Data Index: 621820 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1474088 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6971. Min Act: -0.0000

Data Index: 264395 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1122041 (The Pile)

Max Activating Token Index: 765

Text #8

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6835. Min Act: -0.0000

Data Index: 699018 (The Pile)

Max Activating Token Index: 783

Text #9

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1520807 (The Pile)

Max Activating Token Index: 217

Text #10

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1216713 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6439. Min Act: -0.0000

Data Index: 653320 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6545. Min Act: -0.0000

Data Index: 982143 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1510283 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6723. Min Act: -0.0000

Data Index: 276477 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6539. Min Act: -0.0000

Data Index: 406854 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6055. Min Act: -0.0000

Data Index: 327080 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6415. Min Act: -0.0000

Data Index: 289143 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1787502 (The Pile)

Max Activating Token Index: 317

Text #19

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1153163 (The Pile)

Max Activating Token Index: 990