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

Dataset: Open Web Text

Neuron 594 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: 3.6498. Min Range: -3.6498

Max Act: 3.6439. Min Act: -0.1700

Data Index: 7634746 (Open Web Text)

Max Activating Token Index: 32

Text #1

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.6498. Min Act: -0.1700

Data Index: 2480545 (Open Web Text)

Max Activating Token Index: 340

Text #2

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5746. Min Act: -0.1700

Data Index: 3365245 (Open Web Text)

Max Activating Token Index: 276

Text #3

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5682. Min Act: -0.1700

Data Index: 4950583 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.5268. Min Act: -0.1700

Data Index: 8150157 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4785. Min Act: -0.1700

Data Index: 2977602 (Open Web Text)

Max Activating Token Index: 491

Text #6

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4525. Min Act: -0.1700

Data Index: 617710 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4242. Min Act: -0.1700

Data Index: 5766385 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4658. Min Act: -0.1700

Data Index: 8733459 (Open Web Text)

Max Activating Token Index: 405

Text #9

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4176. Min Act: -0.1700

Data Index: 2905588 (Open Web Text)

Max Activating Token Index: 346

Text #10

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4124. Min Act: -0.1700

Data Index: 5398780 (Open Web Text)

Max Activating Token Index: 367

Text #11

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4242. Min Act: -0.1700

Data Index: 4181767 (Open Web Text)

Max Activating Token Index: 206

Text #12

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4236. Min Act: -0.1700

Data Index: 3827185 (Open Web Text)

Max Activating Token Index: 856

Text #13

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4256. Min Act: -0.1700

Data Index: 5398518 (Open Web Text)

Max Activating Token Index: 136

Text #14

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.3896. Min Act: -0.1700

Data Index: 7190026 (Open Web Text)

Max Activating Token Index: 430

Text #15

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4110. Min Act: -0.1700

Data Index: 7579284 (Open Web Text)

Max Activating Token Index: 737

Text #16

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.3697. Min Act: -0.1700

Data Index: 1021831 (Open Web Text)

Max Activating Token Index: 722

Text #17

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4042. Min Act: -0.1700

Data Index: 526431 (Open Web Text)

Max Activating Token Index: 795

Text #18

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.3861. Min Act: -0.1700

Data Index: 1143988 (Open Web Text)

Max Activating Token Index: 488

Text #19

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.3629. Min Act: -0.1700

Data Index: 960607 (Open Web Text)

Max Activating Token Index: 68