Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 396 in Layer 30

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.6771. Min Act: -0.1700

Data Index: 700127 (Open Web Text)

Max Activating Token Index: 365

Text #1

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.5834. Min Act: -0.1700

Data Index: 6777481 (Open Web Text)

Max Activating Token Index: 346

Text #2

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.5209. Min Act: -0.1700

Data Index: 6914107 (Open Web Text)

Max Activating Token Index: 455

Text #3

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4584. Min Act: -0.1700

Data Index: 5083841 (Open Web Text)

Max Activating Token Index: 748

Text #4

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4271. Min Act: -0.1700

Data Index: 1092258 (Open Web Text)

Max Activating Token Index: 342

Text #5

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4271. Min Act: -0.1700

Data Index: 1358025 (Open Web Text)

Max Activating Token Index: 413

Text #6

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4271. Min Act: -0.1700

Data Index: 5290191 (Open Web Text)

Max Activating Token Index: 135

Text #7

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.3959. Min Act: -0.1700

Data Index: 2955962 (Open Web Text)

Max Activating Token Index: 240

Text #8

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4584. Min Act: -0.1700

Data Index: 6782370 (Open Web Text)

Max Activating Token Index: 283

Text #9

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4271. Min Act: -0.1700

Data Index: 197424 (Open Web Text)

Max Activating Token Index: 393

Text #10

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.3646. Min Act: -0.1700

Data Index: 4639082 (Open Web Text)

Max Activating Token Index: 380

Text #11

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.3021. Min Act: -0.1700

Data Index: 7070923 (Open Web Text)

Max Activating Token Index: 505

Text #12

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.3021. Min Act: -0.1700

Data Index: 1728063 (Open Web Text)

Max Activating Token Index: 326

Text #13

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.3021. Min Act: -0.1700

Data Index: 3323040 (Open Web Text)

Max Activating Token Index: 906

Text #14

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.2709. Min Act: -0.1700

Data Index: 3330693 (Open Web Text)

Max Activating Token Index: 879

Text #15

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.2709. Min Act: -0.1700

Data Index: 717195 (Open Web Text)

Max Activating Token Index: 190

Text #16

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.2709. Min Act: -0.1700

Data Index: 7924067 (Open Web Text)

Max Activating Token Index: 626

Text #17

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.2396. Min Act: -0.1700

Data Index: 1720289 (Open Web Text)

Max Activating Token Index: 583

Text #18

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.2396. Min Act: -0.1700

Data Index: 1372544 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.2396. Min Act: -0.1700

Data Index: 1062469 (Open Web Text)

Max Activating Token Index: 383