Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3591 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.5276. Min Act: -0.0000

Data Index: 1339120 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.3372. Min Act: -0.0000

Data Index: 231293 (The Pile)

Max Activating Token Index: 659

Text #2

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.2397. Min Act: -0.0000

Data Index: 419010 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.2392. Min Act: -0.0000

Data Index: 376153 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1888902 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.1067. Min Act: -0.0000

Data Index: 520877 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.1250. Min Act: -0.0000

Data Index: 321473 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9781. Min Act: -0.0000

Data Index: 220845 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.1107. Min Act: -0.0000

Data Index: 205587 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9314. Min Act: -0.0000

Data Index: 859516 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1586942 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.0101. Min Act: -0.0000

Data Index: 102870 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.0150. Min Act: -0.0000

Data Index: 1304128 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1436121 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9269. Min Act: -0.0000

Data Index: 528356 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9439. Min Act: -0.0000

Data Index: 532232 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.0933. Min Act: -0.0000

Data Index: 139944 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9333. Min Act: -0.0000

Data Index: 894674 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1569100 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.0195. Min Act: -0.0000

Data Index: 402153 (The Pile)

Max Activating Token Index: 1018