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

Dataset: Open Web Text

Neuron 2534 in Layer 6

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: 6.3147. Min Range: -6.3147

Max Act: 6.3147. Min Act: -0.1700

Data Index: 7908466 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 6.3147. Min Range: -6.3147

Max Act: 6.2523. Min Act: -0.1700

Data Index: 8436203 (Open Web Text)

Max Activating Token Index: 949

Text #2

Max Range: 6.3147. Min Range: -6.3147

Max Act: 6.1321. Min Act: -0.1700

Data Index: 6825028 (Open Web Text)

Max Activating Token Index: 614

Text #3

Max Range: 6.3147. Min Range: -6.3147

Max Act: 6.0606. Min Act: -0.1700

Data Index: 2501609 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 6.3147. Min Range: -6.3147

Max Act: 6.0632. Min Act: -0.1700

Data Index: 2636782 (Open Web Text)

Max Activating Token Index: 843

Text #5

Max Range: 6.3147. Min Range: -6.3147

Max Act: 6.0284. Min Act: -0.1700

Data Index: 1743269 (Open Web Text)

Max Activating Token Index: 675

Text #6

Max Range: 6.3147. Min Range: -6.3147

Max Act: 6.0099. Min Act: -0.1700

Data Index: 1579311 (Open Web Text)

Max Activating Token Index: 960

Text #7

Max Range: 6.3147. Min Range: -6.3147

Max Act: 6.0132. Min Act: -0.1700

Data Index: 1375507 (Open Web Text)

Max Activating Token Index: 559

Text #8

Max Range: 6.3147. Min Range: -6.3147

Max Act: 6.0462. Min Act: -0.1700

Data Index: 33013 (Open Web Text)

Max Activating Token Index: 274

Text #9

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.9188. Min Act: -0.1700

Data Index: 4349435 (Open Web Text)

Max Activating Token Index: 67

Text #10

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.9575. Min Act: -0.1700

Data Index: 4362004 (Open Web Text)

Max Activating Token Index: 1008

Text #11

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.9730. Min Act: -0.1700

Data Index: 210880 (Open Web Text)

Max Activating Token Index: 217

Text #12

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.9713. Min Act: -0.1700

Data Index: 249845 (Open Web Text)

Max Activating Token Index: 324

Text #13

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.9586. Min Act: -0.1700

Data Index: 2668264 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.9365. Min Act: -0.1700

Data Index: 115952 (Open Web Text)

Max Activating Token Index: 870

Text #15

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.9272. Min Act: -0.1700

Data Index: 5139111 (Open Web Text)

Max Activating Token Index: 855

Text #16

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.9151. Min Act: -0.1700

Data Index: 2671294 (Open Web Text)

Max Activating Token Index: 364

Text #17

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.9323. Min Act: -0.1700

Data Index: 8456412 (Open Web Text)

Max Activating Token Index: 693

Text #18

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.9398. Min Act: -0.1700

Data Index: 3126236 (Open Web Text)

Max Activating Token Index: 125

Text #19

Max Range: 6.3147. Min Range: -6.3147

Max Act: 5.8807. Min Act: -0.1700

Data Index: 6197034 (Open Web Text)

Max Activating Token Index: 245