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

Dataset: Open Web Text

Neuron 2594 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: 3.8112. Min Range: -3.8112

Max Act: 3.8112. Min Act: -0.1700

Data Index: 446080 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.7334. Min Act: -0.1700

Data Index: 6774999 (Open Web Text)

Max Activating Token Index: 891

Text #2

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.7539. Min Act: -0.1700

Data Index: 5186793 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6871. Min Act: -0.1700

Data Index: 4900439 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6666. Min Act: -0.1700

Data Index: 3606462 (Open Web Text)

Max Activating Token Index: 786

Text #5

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6316. Min Act: -0.1700

Data Index: 4454105 (Open Web Text)

Max Activating Token Index: 394

Text #6

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6269. Min Act: -0.1700

Data Index: 3211176 (Open Web Text)

Max Activating Token Index: 574

Text #7

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6287. Min Act: -0.1700

Data Index: 6686717 (Open Web Text)

Max Activating Token Index: 479

Text #8

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.5960. Min Act: -0.1700

Data Index: 1837762 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6014. Min Act: -0.1700

Data Index: 5062395 (Open Web Text)

Max Activating Token Index: 83

Text #10

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6116. Min Act: -0.1700

Data Index: 4996341 (Open Web Text)

Max Activating Token Index: 343

Text #11

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6090. Min Act: -0.1700

Data Index: 2282617 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6173. Min Act: -0.1700

Data Index: 5439358 (Open Web Text)

Max Activating Token Index: 481

Text #13

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6216. Min Act: -0.1700

Data Index: 2190720 (Open Web Text)

Max Activating Token Index: 664

Text #14

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.5712. Min Act: -0.1700

Data Index: 2457403 (Open Web Text)

Max Activating Token Index: 741

Text #15

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.6013. Min Act: -0.1700

Data Index: 8219419 (Open Web Text)

Max Activating Token Index: 548

Text #16

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.5623. Min Act: -0.1700

Data Index: 5095575 (Open Web Text)

Max Activating Token Index: 224

Text #17

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.5807. Min Act: -0.1700

Data Index: 128965 (Open Web Text)

Max Activating Token Index: 93

Text #18

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.5494. Min Act: -0.1700

Data Index: 4995805 (Open Web Text)

Max Activating Token Index: 679

Text #19

Max Range: 3.8112. Min Range: -3.8112

Max Act: 3.5598. Min Act: -0.1700

Data Index: 436056 (Open Web Text)

Max Activating Token Index: 119