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

Dataset: Open Web Text

Neuron 906 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: 3.9224. Min Range: -3.9224

Max Act: 3.9224. Min Act: -0.1700

Data Index: 8775440 (Open Web Text)

Max Activating Token Index: 861

Text #1

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.8768. Min Act: -0.1700

Data Index: 2938472 (Open Web Text)

Max Activating Token Index: 834

Text #2

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.7491. Min Act: -0.1700

Data Index: 4220907 (Open Web Text)

Max Activating Token Index: 58

Text #3

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.7289. Min Act: -0.1700

Data Index: 7376152 (Open Web Text)

Max Activating Token Index: 417

Text #4

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6813. Min Act: -0.1700

Data Index: 8262246 (Open Web Text)

Max Activating Token Index: 90

Text #5

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.7152. Min Act: -0.1700

Data Index: 4357340 (Open Web Text)

Max Activating Token Index: 592

Text #6

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6864. Min Act: -0.1700

Data Index: 4686978 (Open Web Text)

Max Activating Token Index: 191

Text #7

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6850. Min Act: -0.1700

Data Index: 1125465 (Open Web Text)

Max Activating Token Index: 229

Text #8

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6759. Min Act: -0.1700

Data Index: 7507581 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6564. Min Act: -0.1700

Data Index: 995353 (Open Web Text)

Max Activating Token Index: 616

Text #10

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6649. Min Act: -0.1700

Data Index: 3636751 (Open Web Text)

Max Activating Token Index: 328

Text #11

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6660. Min Act: -0.1700

Data Index: 480186 (Open Web Text)

Max Activating Token Index: 102

Text #12

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6541. Min Act: -0.1700

Data Index: 1052819 (Open Web Text)

Max Activating Token Index: 449

Text #13

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6558. Min Act: -0.1700

Data Index: 4603225 (Open Web Text)

Max Activating Token Index: 591

Text #14

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6168. Min Act: -0.1700

Data Index: 5120255 (Open Web Text)

Max Activating Token Index: 504

Text #15

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.5802. Min Act: -0.1700

Data Index: 5122402 (Open Web Text)

Max Activating Token Index: 487

Text #16

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6403. Min Act: -0.1700

Data Index: 7406543 (Open Web Text)

Max Activating Token Index: 738

Text #17

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6320. Min Act: -0.1700

Data Index: 2813130 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.6497. Min Act: -0.1700

Data Index: 6051945 (Open Web Text)

Max Activating Token Index: 515

Text #19

Max Range: 3.9224. Min Range: -3.9224

Max Act: 3.5831. Min Act: -0.1700

Data Index: 2208113 (Open Web Text)

Max Activating Token Index: 556