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

Dataset: Open Web Text

Neuron 2882 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: 6.1035. Min Range: -6.1035

Max Act: 6.1035. Min Act: -0.1700

Data Index: 4460685 (Open Web Text)

Max Activating Token Index: 762

Text #1

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.8905. Min Act: -0.1700

Data Index: 6541253 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.9053. Min Act: -0.1697

Data Index: 8588254 (Open Web Text)

Max Activating Token Index: 474

Text #3

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.8863. Min Act: -0.1700

Data Index: 8475919 (Open Web Text)

Max Activating Token Index: 485

Text #4

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.8156. Min Act: -0.1700

Data Index: 2511916 (Open Web Text)

Max Activating Token Index: 198

Text #5

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.7947. Min Act: -0.1700

Data Index: 308985 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.8033. Min Act: -0.1700

Data Index: 8441455 (Open Web Text)

Max Activating Token Index: 519

Text #7

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.8064. Min Act: -0.1699

Data Index: 6615303 (Open Web Text)

Max Activating Token Index: 973

Text #8

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.7343. Min Act: -0.1700

Data Index: 4624379 (Open Web Text)

Max Activating Token Index: 451

Text #9

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.7740. Min Act: -0.1700

Data Index: 6598309 (Open Web Text)

Max Activating Token Index: 535

Text #10

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.7525. Min Act: -0.1700

Data Index: 2061308 (Open Web Text)

Max Activating Token Index: 140

Text #11

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.7491. Min Act: -0.1699

Data Index: 4209847 (Open Web Text)

Max Activating Token Index: 38

Text #12

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.7073. Min Act: -0.1700

Data Index: 7174226 (Open Web Text)

Max Activating Token Index: 471

Text #13

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.7110. Min Act: -0.1700

Data Index: 588251 (Open Web Text)

Max Activating Token Index: 613

Text #14

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.6510. Min Act: -0.1700

Data Index: 1869432 (Open Web Text)

Max Activating Token Index: 375

Text #15

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.6820. Min Act: -0.1700

Data Index: 2145299 (Open Web Text)

Max Activating Token Index: 770

Text #16

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.6395. Min Act: -0.1700

Data Index: 1937477 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.6910. Min Act: -0.1700

Data Index: 439453 (Open Web Text)

Max Activating Token Index: 487

Text #18

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.6822. Min Act: -0.1700

Data Index: 3275933 (Open Web Text)

Max Activating Token Index: 596

Text #19

Max Range: 6.1035. Min Range: -6.1035

Max Act: 5.6087. Min Act: -0.1700

Data Index: 6554554 (Open Web Text)

Max Activating Token Index: 707