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

Dataset: Open Web Text

Neuron 673 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: 5.3473. Min Range: -5.3473

Max Act: 5.3473. Min Act: -0.1700

Data Index: 5470784 (Open Web Text)

Max Activating Token Index: 197

Text #1

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.2747. Min Act: -0.1700

Data Index: 570200 (Open Web Text)

Max Activating Token Index: 585

Text #2

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.2934. Min Act: -0.1700

Data Index: 7528089 (Open Web Text)

Max Activating Token Index: 930

Text #3

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.2386. Min Act: -0.1700

Data Index: 4254126 (Open Web Text)

Max Activating Token Index: 988

Text #4

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.2114. Min Act: -0.1700

Data Index: 940726 (Open Web Text)

Max Activating Token Index: 862

Text #5

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.1211. Min Act: -0.1700

Data Index: 1851777 (Open Web Text)

Max Activating Token Index: 708

Text #6

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.1372. Min Act: -0.1700

Data Index: 6327165 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.1381. Min Act: -0.1700

Data Index: 4420944 (Open Web Text)

Max Activating Token Index: 353

Text #8

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.1267. Min Act: -0.1700

Data Index: 6716491 (Open Web Text)

Max Activating Token Index: 236

Text #9

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.1281. Min Act: -0.1700

Data Index: 2188396 (Open Web Text)

Max Activating Token Index: 378

Text #10

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.1254. Min Act: -0.1700

Data Index: 4107486 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.0578. Min Act: -0.1700

Data Index: 1339302 (Open Web Text)

Max Activating Token Index: 185

Text #12

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.0912. Min Act: -0.1700

Data Index: 7333592 (Open Web Text)

Max Activating Token Index: 459

Text #13

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.1163. Min Act: -0.1700

Data Index: 2061012 (Open Web Text)

Max Activating Token Index: 329

Text #14

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.0715. Min Act: -0.1700

Data Index: 1769494 (Open Web Text)

Max Activating Token Index: 555

Text #15

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.0432. Min Act: -0.1700

Data Index: 6107728 (Open Web Text)

Max Activating Token Index: 630

Text #16

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.0824. Min Act: -0.1700

Data Index: 2279036 (Open Web Text)

Max Activating Token Index: 860

Text #17

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.0909. Min Act: -0.1700

Data Index: 1076726 (Open Web Text)

Max Activating Token Index: 217

Text #18

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.0428. Min Act: -0.1700

Data Index: 7217733 (Open Web Text)

Max Activating Token Index: 910

Text #19

Max Range: 5.3473. Min Range: -5.3473

Max Act: 5.0121. Min Act: -0.1700

Data Index: 1748110 (Open Web Text)

Max Activating Token Index: 407