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

Dataset: Open Web Text

Neuron 2937 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: 4.8943. Min Range: -4.8943

Max Act: 4.8943. Min Act: -0.1700

Data Index: 2572102 (Open Web Text)

Max Activating Token Index: 641

Text #1

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.3606. Min Act: -0.1700

Data Index: 4879916 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.3682. Min Act: -0.1700

Data Index: 3727869 (Open Web Text)

Max Activating Token Index: 791

Text #3

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.2375. Min Act: -0.1700

Data Index: 3873690 (Open Web Text)

Max Activating Token Index: 665

Text #4

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.2258. Min Act: -0.1700

Data Index: 6210454 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.2335. Min Act: -0.1700

Data Index: 943178 (Open Web Text)

Max Activating Token Index: 956

Text #6

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1635. Min Act: -0.1700

Data Index: 999046 (Open Web Text)

Max Activating Token Index: 871

Text #7

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1959. Min Act: -0.1700

Data Index: 713870 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1621. Min Act: -0.1700

Data Index: 7336587 (Open Web Text)

Max Activating Token Index: 292

Text #9

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1962. Min Act: -0.1700

Data Index: 8761844 (Open Web Text)

Max Activating Token Index: 227

Text #10

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1928. Min Act: -0.1700

Data Index: 1115315 (Open Web Text)

Max Activating Token Index: 111

Text #11

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1523. Min Act: -0.1700

Data Index: 6332746 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1561. Min Act: -0.1700

Data Index: 885533 (Open Web Text)

Max Activating Token Index: 105

Text #13

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1790. Min Act: -0.1700

Data Index: 848390 (Open Web Text)

Max Activating Token Index: 283

Text #14

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1447. Min Act: -0.1700

Data Index: 5447290 (Open Web Text)

Max Activating Token Index: 491

Text #15

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1350. Min Act: -0.1700

Data Index: 653276 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1039. Min Act: -0.1700

Data Index: 4431395 (Open Web Text)

Max Activating Token Index: 671

Text #17

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.0896. Min Act: -0.1700

Data Index: 834039 (Open Web Text)

Max Activating Token Index: 490

Text #18

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.1174. Min Act: -0.1700

Data Index: 3135765 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 4.8943. Min Range: -4.8943

Max Act: 4.0833. Min Act: -0.1700

Data Index: 3064573 (Open Web Text)

Max Activating Token Index: 884