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

Dataset: Open Web Text

Neuron 2501 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: 3.2893. Min Range: -3.2893

Max Act: 3.2893. Min Act: -0.1700

Data Index: 8819944 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.2525. Min Act: -0.1700

Data Index: 5989071 (Open Web Text)

Max Activating Token Index: 406

Text #2

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.2067. Min Act: -0.1700

Data Index: 6694421 (Open Web Text)

Max Activating Token Index: 670

Text #3

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.2110. Min Act: -0.1700

Data Index: 4437248 (Open Web Text)

Max Activating Token Index: 962

Text #4

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1945. Min Act: -0.1700

Data Index: 942450 (Open Web Text)

Max Activating Token Index: 920

Text #5

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1645. Min Act: -0.1700

Data Index: 7736020 (Open Web Text)

Max Activating Token Index: 125

Text #6

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1343. Min Act: -0.1700

Data Index: 6091387 (Open Web Text)

Max Activating Token Index: 246

Text #7

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1359. Min Act: -0.1700

Data Index: 6470016 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1242. Min Act: -0.1700

Data Index: 23172 (Open Web Text)

Max Activating Token Index: 182

Text #9

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1457. Min Act: -0.1700

Data Index: 1207496 (Open Web Text)

Max Activating Token Index: 758

Text #10

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1430. Min Act: -0.1700

Data Index: 8029077 (Open Web Text)

Max Activating Token Index: 118

Text #11

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1454. Min Act: -0.1700

Data Index: 673112 (Open Web Text)

Max Activating Token Index: 324

Text #12

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1295. Min Act: -0.1700

Data Index: 2103522 (Open Web Text)

Max Activating Token Index: 441

Text #13

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1346. Min Act: -0.1700

Data Index: 7903113 (Open Web Text)

Max Activating Token Index: 911

Text #14

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1369. Min Act: -0.1700

Data Index: 6515316 (Open Web Text)

Max Activating Token Index: 759

Text #15

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1167. Min Act: -0.1700

Data Index: 1639484 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1205. Min Act: -0.1700

Data Index: 2774070 (Open Web Text)

Max Activating Token Index: 688

Text #17

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.0844. Min Act: -0.1700

Data Index: 5588809 (Open Web Text)

Max Activating Token Index: 262

Text #18

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.0989. Min Act: -0.1700

Data Index: 808010 (Open Web Text)

Max Activating Token Index: 96

Text #19

Max Range: 3.2893. Min Range: -3.2893

Max Act: 3.1173. Min Act: -0.1700

Data Index: 4673731 (Open Web Text)

Max Activating Token Index: 502