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

Dataset: Open Web Text

Neuron 2268 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: 4.2278. Min Range: -4.2278

Max Act: 4.2278. Min Act: -0.1700

Data Index: 1016955 (Open Web Text)

Max Activating Token Index: 385

Text #1

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.2209. Min Act: -0.1700

Data Index: 8419236 (Open Web Text)

Max Activating Token Index: 884

Text #2

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.1786. Min Act: -0.1700

Data Index: 6026700 (Open Web Text)

Max Activating Token Index: 376

Text #3

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.1587. Min Act: -0.1700

Data Index: 8780406 (Open Web Text)

Max Activating Token Index: 415

Text #4

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.1029. Min Act: -0.1700

Data Index: 7568241 (Open Web Text)

Max Activating Token Index: 69

Text #5

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0736. Min Act: -0.1700

Data Index: 544224 (Open Web Text)

Max Activating Token Index: 835

Text #6

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0784. Min Act: -0.1700

Data Index: 2969134 (Open Web Text)

Max Activating Token Index: 846

Text #7

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0323. Min Act: -0.1700

Data Index: 5534700 (Open Web Text)

Max Activating Token Index: 745

Text #8

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0663. Min Act: -0.1700

Data Index: 8146944 (Open Web Text)

Max Activating Token Index: 364

Text #9

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0506. Min Act: -0.1700

Data Index: 933683 (Open Web Text)

Max Activating Token Index: 346

Text #10

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0257. Min Act: -0.1700

Data Index: 2006831 (Open Web Text)

Max Activating Token Index: 591

Text #11

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0608. Min Act: -0.1700

Data Index: 5333100 (Open Web Text)

Max Activating Token Index: 289

Text #12

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0703. Min Act: -0.1700

Data Index: 1247790 (Open Web Text)

Max Activating Token Index: 557

Text #13

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0829. Min Act: -0.1700

Data Index: 4139744 (Open Web Text)

Max Activating Token Index: 1004

Text #14

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0652. Min Act: -0.1700

Data Index: 3337014 (Open Web Text)

Max Activating Token Index: 791

Text #15

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0183. Min Act: -0.1700

Data Index: 5374965 (Open Web Text)

Max Activating Token Index: 757

Text #16

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0137. Min Act: -0.1700

Data Index: 8039518 (Open Web Text)

Max Activating Token Index: 283

Text #17

Max Range: 4.2278. Min Range: -4.2278

Max Act: 3.9963. Min Act: -0.1700

Data Index: 4745334 (Open Web Text)

Max Activating Token Index: 119

Text #18

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0175. Min Act: -0.1700

Data Index: 6564901 (Open Web Text)

Max Activating Token Index: 505

Text #19

Max Range: 4.2278. Min Range: -4.2278

Max Act: 4.0239. Min Act: -0.1700

Data Index: 5923984 (Open Web Text)

Max Activating Token Index: 929