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

Dataset: The Pile

Neuron 4449 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: 1.7308. Min Range: -1.7308

Max Act: 1.7308. Min Act: -0.0000

Data Index: 1077936 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.6555. Min Act: -0.0000

Data Index: 1726414 (The Pile)

Max Activating Token Index: 178

Text #2

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.4554. Min Act: -0.0000

Data Index: 1134154 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.3886. Min Act: -0.0000

Data Index: 1736977 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.2964. Min Act: -0.0000

Data Index: 1314731 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.4280. Min Act: -0.0000

Data Index: 955040 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1710987 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.4312. Min Act: -0.0000

Data Index: 126929 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.4517. Min Act: -0.0000

Data Index: 1493267 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.3407. Min Act: -0.0000

Data Index: 528353 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.3095. Min Act: -0.0000

Data Index: 598424 (The Pile)

Max Activating Token Index: 616

Text #11

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.4538. Min Act: -0.0000

Data Index: 1869343 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.2524. Min Act: -0.0000

Data Index: 694550 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.3944. Min Act: -0.0000

Data Index: 422332 (The Pile)

Max Activating Token Index: 82

Text #14

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1202607 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.3033. Min Act: -0.0000

Data Index: 1313588 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.2706. Min Act: -0.0000

Data Index: 1574289 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.2286. Min Act: -0.0000

Data Index: 854947 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.3302. Min Act: -0.0000

Data Index: 83075 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 1.7308. Min Range: -1.7308

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1929517 (The Pile)

Max Activating Token Index: 947