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

Dataset: Open Web Text

Neuron 409 in Layer 2

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: 3.2384. Min Range: -3.2384

Max Act: 3.2384. Min Act: -0.1700

Data Index: 436662 (Open Web Text)

Max Activating Token Index: 222

Text #1

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.2020. Min Act: -0.1700

Data Index: 2031841 (Open Web Text)

Max Activating Token Index: 457

Text #2

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1807. Min Act: -0.1700

Data Index: 5107500 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1429. Min Act: -0.1700

Data Index: 5753344 (Open Web Text)

Max Activating Token Index: 763

Text #4

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1336. Min Act: -0.1700

Data Index: 4569431 (Open Web Text)

Max Activating Token Index: 722

Text #5

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1121. Min Act: -0.1700

Data Index: 8663234 (Open Web Text)

Max Activating Token Index: 601

Text #6

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1139. Min Act: -0.1700

Data Index: 1521831 (Open Web Text)

Max Activating Token Index: 262

Text #7

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0731. Min Act: -0.1700

Data Index: 5836795 (Open Web Text)

Max Activating Token Index: 404

Text #8

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0806. Min Act: -0.1700

Data Index: 4544622 (Open Web Text)

Max Activating Token Index: 313

Text #9

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0731. Min Act: -0.1700

Data Index: 3603297 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0599. Min Act: -0.1700

Data Index: 8300578 (Open Web Text)

Max Activating Token Index: 221

Text #11

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0650. Min Act: -0.1700

Data Index: 166891 (Open Web Text)

Max Activating Token Index: 314

Text #12

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0423. Min Act: -0.1700

Data Index: 660754 (Open Web Text)

Max Activating Token Index: 277

Text #13

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0418. Min Act: -0.1700

Data Index: 5030710 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0648. Min Act: -0.1700

Data Index: 4279128 (Open Web Text)

Max Activating Token Index: 515

Text #15

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0409. Min Act: -0.1700

Data Index: 7058065 (Open Web Text)

Max Activating Token Index: 53

Text #16

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0376. Min Act: -0.1700

Data Index: 5545020 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0315. Min Act: -0.1700

Data Index: 6687221 (Open Web Text)

Max Activating Token Index: 841

Text #18

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0502. Min Act: -0.1700

Data Index: 5028293 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0205. Min Act: -0.1700

Data Index: 6186946 (Open Web Text)

Max Activating Token Index: 1023