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

Dataset: Open Web Text

Neuron 2997 in Layer 0

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: 4.0943. Min Range: -4.0943

Max Act: 4.0943. Min Act: -0.1700

Data Index: 2325484 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9316. Min Act: -0.1700

Data Index: 2325483 (Open Web Text)

Max Activating Token Index: 890

Text #2

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.7949. Min Act: -0.1700

Data Index: 6052661 (Open Web Text)

Max Activating Token Index: 971

Text #3

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.6246. Min Act: -0.1700

Data Index: 4443278 (Open Web Text)

Max Activating Token Index: 369

Text #4

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.6189. Min Act: -0.1700

Data Index: 5251024 (Open Web Text)

Max Activating Token Index: 760

Text #5

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5790. Min Act: -0.1700

Data Index: 5908103 (Open Web Text)

Max Activating Token Index: 434

Text #6

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5669. Min Act: -0.1700

Data Index: 5787260 (Open Web Text)

Max Activating Token Index: 330

Text #7

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5638. Min Act: -0.1700

Data Index: 5787250 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5666. Min Act: -0.1700

Data Index: 5787254 (Open Web Text)

Max Activating Token Index: 357

Text #9

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5674. Min Act: -0.1700

Data Index: 5908105 (Open Web Text)

Max Activating Token Index: 517

Text #10

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5844. Min Act: -0.1700

Data Index: 7596542 (Open Web Text)

Max Activating Token Index: 240

Text #11

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5461. Min Act: -0.1700

Data Index: 5787241 (Open Web Text)

Max Activating Token Index: 474

Text #12

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5146. Min Act: -0.1700

Data Index: 5787280 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5266. Min Act: -0.1700

Data Index: 5787278 (Open Web Text)

Max Activating Token Index: 564

Text #14

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5440. Min Act: -0.1700

Data Index: 5908107 (Open Web Text)

Max Activating Token Index: 440

Text #15

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5313. Min Act: -0.1700

Data Index: 2704523 (Open Web Text)

Max Activating Token Index: 456

Text #16

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5394. Min Act: -0.1700

Data Index: 5787279 (Open Web Text)

Max Activating Token Index: 473

Text #17

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5280. Min Act: -0.1700

Data Index: 5787248 (Open Web Text)

Max Activating Token Index: 665

Text #18

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5016. Min Act: -0.1700

Data Index: 4197943 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.5355. Min Act: -0.1700

Data Index: 5787255 (Open Web Text)

Max Activating Token Index: 676