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

Dataset: Open Web Text

Neuron 702 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: 4.6977. Min Range: -4.6977

Max Act: 4.6977. Min Act: -0.1700

Data Index: 5863969 (Open Web Text)

Max Activating Token Index: 544

Text #1

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.6360. Min Act: -0.1700

Data Index: 8727794 (Open Web Text)

Max Activating Token Index: 399

Text #2

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.6329. Min Act: -0.1700

Data Index: 1942112 (Open Web Text)

Max Activating Token Index: 511

Text #3

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.6018. Min Act: -0.1700

Data Index: 4825660 (Open Web Text)

Max Activating Token Index: 715

Text #4

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.5971. Min Act: -0.1700

Data Index: 1856342 (Open Web Text)

Max Activating Token Index: 558

Text #5

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.5875. Min Act: -0.1700

Data Index: 4386204 (Open Web Text)

Max Activating Token Index: 647

Text #6

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.5255. Min Act: -0.1700

Data Index: 6178437 (Open Web Text)

Max Activating Token Index: 893

Text #7

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.5354. Min Act: -0.1700

Data Index: 6240392 (Open Web Text)

Max Activating Token Index: 749

Text #8

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.5710. Min Act: -0.1699

Data Index: 7040026 (Open Web Text)

Max Activating Token Index: 473

Text #9

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.5402. Min Act: -0.1700

Data Index: 2671871 (Open Web Text)

Max Activating Token Index: 148

Text #10

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.4833. Min Act: -0.1700

Data Index: 4097125 (Open Web Text)

Max Activating Token Index: 962

Text #11

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.5162. Min Act: -0.1700

Data Index: 2471533 (Open Web Text)

Max Activating Token Index: 378

Text #12

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.5079. Min Act: -0.1700

Data Index: 4062216 (Open Web Text)

Max Activating Token Index: 387

Text #13

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.5217. Min Act: -0.1700

Data Index: 3295227 (Open Web Text)

Max Activating Token Index: 954

Text #14

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.4595. Min Act: -0.1700

Data Index: 3121291 (Open Web Text)

Max Activating Token Index: 293

Text #15

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.4980. Min Act: -0.1700

Data Index: 8563004 (Open Web Text)

Max Activating Token Index: 157

Text #16

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.4463. Min Act: -0.1700

Data Index: 3444870 (Open Web Text)

Max Activating Token Index: 89

Text #17

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.4808. Min Act: -0.1696

Data Index: 8788486 (Open Web Text)

Max Activating Token Index: 510

Text #18

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.4927. Min Act: -0.1700

Data Index: 196253 (Open Web Text)

Max Activating Token Index: 549

Text #19

Max Range: 4.6977. Min Range: -4.6977

Max Act: 4.4479. Min Act: -0.1700

Data Index: 1502439 (Open Web Text)

Max Activating Token Index: 249