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

Dataset: Open Web Text

Neuron 627 in Layer 3

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: 4.3518. Min Range: -4.3518

Max Act: 4.3518. Min Act: -0.1700

Data Index: 6598801 (Open Web Text)

Max Activating Token Index: 220

Text #1

Max Range: 4.3518. Min Range: -4.3518

Max Act: 4.2319. Min Act: -0.1700

Data Index: 2444240 (Open Web Text)

Max Activating Token Index: 717

Text #2

Max Range: 4.3518. Min Range: -4.3518

Max Act: 4.1131. Min Act: -0.1700

Data Index: 4578307 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.3518. Min Range: -4.3518

Max Act: 4.0524. Min Act: -0.1700

Data Index: 924915 (Open Web Text)

Max Activating Token Index: 910

Text #4

Max Range: 4.3518. Min Range: -4.3518

Max Act: 4.0513. Min Act: -0.1700

Data Index: 5634633 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 4.3518. Min Range: -4.3518

Max Act: 4.0484. Min Act: -0.1700

Data Index: 5614665 (Open Web Text)

Max Activating Token Index: 850

Text #6

Max Range: 4.3518. Min Range: -4.3518

Max Act: 4.0150. Min Act: -0.1700

Data Index: 2283494 (Open Web Text)

Max Activating Token Index: 987

Text #7

Max Range: 4.3518. Min Range: -4.3518

Max Act: 4.0475. Min Act: -0.1700

Data Index: 1967037 (Open Web Text)

Max Activating Token Index: 871

Text #8

Max Range: 4.3518. Min Range: -4.3518

Max Act: 4.0200. Min Act: -0.1700

Data Index: 4500459 (Open Web Text)

Max Activating Token Index: 532

Text #9

Max Range: 4.3518. Min Range: -4.3518

Max Act: 3.9891. Min Act: -0.1700

Data Index: 1999614 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 4.3518. Min Range: -4.3518

Max Act: 3.9609. Min Act: -0.1700

Data Index: 5254434 (Open Web Text)

Max Activating Token Index: 826

Text #11

Max Range: 4.3518. Min Range: -4.3518

Max Act: 3.9909. Min Act: -0.1700

Data Index: 7298641 (Open Web Text)

Max Activating Token Index: 243

Text #12

Max Range: 4.3518. Min Range: -4.3518

Max Act: 3.9771. Min Act: -0.1700

Data Index: 1528063 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 4.3518. Min Range: -4.3518

Max Act: 4.0066. Min Act: -0.1700

Data Index: 6165372 (Open Web Text)

Max Activating Token Index: 683

Text #14

Max Range: 4.3518. Min Range: -4.3518

Max Act: 3.9638. Min Act: -0.1700

Data Index: 503303 (Open Web Text)

Max Activating Token Index: 167

Text #15

Max Range: 4.3518. Min Range: -4.3518

Max Act: 3.9384. Min Act: -0.1700

Data Index: 1929704 (Open Web Text)

Max Activating Token Index: 144

Text #16

Max Range: 4.3518. Min Range: -4.3518

Max Act: 3.9373. Min Act: -0.1700

Data Index: 640984 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 4.3518. Min Range: -4.3518

Max Act: 3.9445. Min Act: -0.1700

Data Index: 1316215 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 4.3518. Min Range: -4.3518

Max Act: 3.9359. Min Act: -0.1700

Data Index: 5366137 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 4.3518. Min Range: -4.3518

Max Act: 3.9479. Min Act: -0.1700

Data Index: 5382513 (Open Web Text)

Max Activating Token Index: 803