Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2107 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.6051. Min Act: -0.1700

Data Index: 8398316 (Open Web Text)

Max Activating Token Index: 185

Text #1

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.5698. Min Act: -0.1700

Data Index: 5085472 (Open Web Text)

Max Activating Token Index: 763

Text #2

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.5692. Min Act: -0.1700

Data Index: 8252541 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.5613. Min Act: -0.1700

Data Index: 1311000 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.5218. Min Act: -0.1700

Data Index: 7079227 (Open Web Text)

Max Activating Token Index: 205

Text #5

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.5340. Min Act: -0.1700

Data Index: 3842926 (Open Web Text)

Max Activating Token Index: 119

Text #6

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.5387. Min Act: -0.1700

Data Index: 7605495 (Open Web Text)

Max Activating Token Index: 528

Text #7

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.5641. Min Act: -0.1700

Data Index: 1356511 (Open Web Text)

Max Activating Token Index: 361

Text #8

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.5132. Min Act: -0.1700

Data Index: 2083719 (Open Web Text)

Max Activating Token Index: 120

Text #9

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4868. Min Act: -0.1700

Data Index: 2413457 (Open Web Text)

Max Activating Token Index: 275

Text #10

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4765. Min Act: -0.1700

Data Index: 6882237 (Open Web Text)

Max Activating Token Index: 466

Text #11

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4560. Min Act: -0.1700

Data Index: 2883203 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4591. Min Act: -0.1700

Data Index: 2736534 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4617. Min Act: -0.1700

Data Index: 654029 (Open Web Text)

Max Activating Token Index: 44

Text #14

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4810. Min Act: -0.1700

Data Index: 2607121 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4709. Min Act: -0.1700

Data Index: 6859262 (Open Web Text)

Max Activating Token Index: 148

Text #16

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4695. Min Act: -0.1700

Data Index: 1947104 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4685. Min Act: -0.1700

Data Index: 7550878 (Open Web Text)

Max Activating Token Index: 426

Text #18

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4602. Min Act: -0.1700

Data Index: 3587881 (Open Web Text)

Max Activating Token Index: 650

Text #19

Max Range: 4.6051. Min Range: -4.6051

Max Act: 4.4426. Min Act: -0.1700

Data Index: 935925 (Open Web Text)

Max Activating Token Index: 7