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

Dataset: The Pile

Neuron 4736 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.8482. Min Act: -0.0000

Data Index: 1578978 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.3956. Min Act: -0.0000

Data Index: 1110174 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.4135. Min Act: -0.0000

Data Index: 1142299 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.2173. Min Act: -0.0000

Data Index: 1737394 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.3752. Min Act: -0.0000

Data Index: 438955 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.2312. Min Act: -0.0000

Data Index: 1999611 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.3752. Min Act: -0.0000

Data Index: 1090633 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.3552. Min Act: -0.0000

Data Index: 430426 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.1551. Min Act: -0.0000

Data Index: 539998 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.1480. Min Act: -0.0000

Data Index: 1109100 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.1422. Min Act: -0.0000

Data Index: 1302781 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.1325. Min Act: -0.0000

Data Index: 1223638 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.1300. Min Act: -0.0000

Data Index: 1557340 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.1228. Min Act: -0.0000

Data Index: 1442328 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.2456. Min Act: -0.0000

Data Index: 527002 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.2548. Min Act: -0.0000

Data Index: 562131 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.1289. Min Act: -0.0000

Data Index: 332417 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.0778. Min Act: -0.0000

Data Index: 1131262 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.0332. Min Act: -0.0000

Data Index: 1455407 (The Pile)

Max Activating Token Index: 498

Text #19

Max Range: 3.8482. Min Range: -3.8482

Max Act: 2.9959. Min Act: -0.0000

Data Index: 182915 (The Pile)

Max Activating Token Index: 525