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

Dataset: Open Web Text

Neuron 1391 in Layer 4

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: 3.4576. Min Range: -3.4576

Max Act: 3.4576. Min Act: -0.1700

Data Index: 8422003 (Open Web Text)

Max Activating Token Index: 595

Text #1

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.4274. Min Act: -0.1700

Data Index: 1957179 (Open Web Text)

Max Activating Token Index: 463

Text #2

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.3735. Min Act: -0.1700

Data Index: 6341916 (Open Web Text)

Max Activating Token Index: 779

Text #3

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.3568. Min Act: -0.1700

Data Index: 1848791 (Open Web Text)

Max Activating Token Index: 297

Text #4

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.3589. Min Act: -0.1700

Data Index: 3806450 (Open Web Text)

Max Activating Token Index: 1018

Text #5

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.3065. Min Act: -0.1700

Data Index: 7597761 (Open Web Text)

Max Activating Token Index: 837

Text #6

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.3228. Min Act: -0.1700

Data Index: 257227 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.3377. Min Act: -0.1700

Data Index: 5046156 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.3203. Min Act: -0.1700

Data Index: 5832201 (Open Web Text)

Max Activating Token Index: 642

Text #9

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.3390. Min Act: -0.1700

Data Index: 8600173 (Open Web Text)

Max Activating Token Index: 711

Text #10

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.2990. Min Act: -0.1700

Data Index: 7597765 (Open Web Text)

Max Activating Token Index: 449

Text #11

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.3099. Min Act: -0.1700

Data Index: 693206 (Open Web Text)

Max Activating Token Index: 60

Text #12

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.2584. Min Act: -0.1700

Data Index: 590111 (Open Web Text)

Max Activating Token Index: 625

Text #13

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.2867. Min Act: -0.1700

Data Index: 3221879 (Open Web Text)

Max Activating Token Index: 431

Text #14

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.2814. Min Act: -0.1700

Data Index: 699592 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.2985. Min Act: -0.1700

Data Index: 1533627 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.2882. Min Act: -0.1700

Data Index: 8785075 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.2598. Min Act: -0.1700

Data Index: 6735761 (Open Web Text)

Max Activating Token Index: 807

Text #18

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.2635. Min Act: -0.1700

Data Index: 5382958 (Open Web Text)

Max Activating Token Index: 57

Text #19

Max Range: 3.4576. Min Range: -3.4576

Max Act: 3.2247. Min Act: -0.1700

Data Index: 2613753 (Open Web Text)

Max Activating Token Index: 155