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

Dataset: The Pile

Neuron 803 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: 3.8305. Min Range: -3.8305

Max Act: 3.8305. Min Act: -0.0000

Data Index: 1226236 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 3.8305. Min Range: -3.8305

Max Act: 2.3493. Min Act: -0.0000

Data Index: 1082325 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 3.8305. Min Range: -3.8305

Max Act: 2.3147. Min Act: -0.0000

Data Index: 1934748 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 3.8305. Min Range: -3.8305

Max Act: 2.1196. Min Act: -0.0000

Data Index: 1991350 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 3.8305. Min Range: -3.8305

Max Act: 2.1170. Min Act: -0.0000

Data Index: 157795 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 3.8305. Min Range: -3.8305

Max Act: 2.0957. Min Act: -0.0000

Data Index: 213427 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.9754. Min Act: -0.0000

Data Index: 962101 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 3.8305. Min Range: -3.8305

Max Act: 2.2552. Min Act: -0.0000

Data Index: 994366 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.9274. Min Act: -0.0000

Data Index: 1493756 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.9569. Min Act: -0.0000

Data Index: 141051 (The Pile)

Max Activating Token Index: 375

Text #10

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.9459. Min Act: -0.0000

Data Index: 472374 (The Pile)

Max Activating Token Index: 542

Text #11

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.9986. Min Act: -0.0000

Data Index: 1881088 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.8047. Min Act: -0.0000

Data Index: 964806 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.7860. Min Act: -0.0000

Data Index: 805724 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.7891. Min Act: -0.0000

Data Index: 1676382 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.5960. Min Act: -0.0000

Data Index: 1343449 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.7843. Min Act: -0.0000

Data Index: 1513554 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.6441. Min Act: -0.0000

Data Index: 1429622 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.7731. Min Act: -0.0000

Data Index: 7748 (The Pile)

Max Activating Token Index: 895

Text #19

Max Range: 3.8305. Min Range: -3.8305

Max Act: 1.9372. Min Act: -0.0000

Data Index: 88597 (The Pile)

Max Activating Token Index: 758