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

Dataset: Open Web Text

Neuron 2627 in Layer 6

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: 4.4084. Min Range: -4.4084

Max Act: 4.4084. Min Act: -0.1700

Data Index: 8381319 (Open Web Text)

Max Activating Token Index: 404

Text #1

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.3264. Min Act: -0.1700

Data Index: 3665791 (Open Web Text)

Max Activating Token Index: 238

Text #2

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.3216. Min Act: -0.1700

Data Index: 326977 (Open Web Text)

Max Activating Token Index: 560

Text #3

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.2889. Min Act: -0.1700

Data Index: 776196 (Open Web Text)

Max Activating Token Index: 905

Text #4

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.3063. Min Act: -0.1700

Data Index: 7397484 (Open Web Text)

Max Activating Token Index: 28

Text #5

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.3134. Min Act: -0.1700

Data Index: 5073782 (Open Web Text)

Max Activating Token Index: 660

Text #6

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.2726. Min Act: -0.1700

Data Index: 4746260 (Open Web Text)

Max Activating Token Index: 108

Text #7

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.2345. Min Act: -0.1700

Data Index: 7620774 (Open Web Text)

Max Activating Token Index: 686

Text #8

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.2534. Min Act: -0.1700

Data Index: 4963995 (Open Web Text)

Max Activating Token Index: 744

Text #9

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.2683. Min Act: -0.1700

Data Index: 860354 (Open Web Text)

Max Activating Token Index: 393

Text #10

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.2594. Min Act: -0.1700

Data Index: 7050371 (Open Web Text)

Max Activating Token Index: 861

Text #11

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.1945. Min Act: -0.1700

Data Index: 4447535 (Open Web Text)

Max Activating Token Index: 630

Text #12

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.2494. Min Act: -0.1700

Data Index: 6250669 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.2078. Min Act: -0.1700

Data Index: 4252900 (Open Web Text)

Max Activating Token Index: 450

Text #14

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.1798. Min Act: -0.1700

Data Index: 1256863 (Open Web Text)

Max Activating Token Index: 771

Text #15

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.2053. Min Act: -0.1700

Data Index: 7731810 (Open Web Text)

Max Activating Token Index: 526

Text #16

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.1806. Min Act: -0.1700

Data Index: 3117600 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.1723. Min Act: -0.1700

Data Index: 6493535 (Open Web Text)

Max Activating Token Index: 143

Text #18

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.1694. Min Act: -0.1700

Data Index: 5022692 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 4.4084. Min Range: -4.4084

Max Act: 4.1459. Min Act: -0.1700

Data Index: 4777411 (Open Web Text)

Max Activating Token Index: 277