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

Dataset: The Pile

Neuron 1068 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.4463. Min Act: -0.0000

Data Index: 445650 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1256425 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3394. Min Act: -0.0000

Data Index: 58389 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1640067 (The Pile)

Max Activating Token Index: 437

Text #4

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1195520 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3226. Min Act: -0.0000

Data Index: 916388 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1385170 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3148. Min Act: -0.0000

Data Index: 853064 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3033. Min Act: -0.0000

Data Index: 777775 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1201837 (The Pile)

Max Activating Token Index: 394

Text #10

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1009291 (The Pile)

Max Activating Token Index: 669

Text #11

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1993804 (The Pile)

Max Activating Token Index: 81

Text #12

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1709476 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1039375 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1917702 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2665. Min Act: -0.0000

Data Index: 954362 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1222178 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1882199 (The Pile)

Max Activating Token Index: 103

Text #18

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1974095 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1890983 (The Pile)

Max Activating Token Index: 684