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

Dataset: Open Web Text

Neuron 2698 in Layer 2

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: 1.8113. Min Range: -1.8113

Max Act: 1.8113. Min Act: -0.1700

Data Index: 982741 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.8075. Min Act: -0.1700

Data Index: 5263234 (Open Web Text)

Max Activating Token Index: 160

Text #2

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.8036. Min Act: -0.1700

Data Index: 5710056 (Open Web Text)

Max Activating Token Index: 147

Text #3

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7721. Min Act: -0.1700

Data Index: 3717403 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7835. Min Act: -0.1700

Data Index: 920569 (Open Web Text)

Max Activating Token Index: 226

Text #5

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7516. Min Act: -0.1700

Data Index: 182188 (Open Web Text)

Max Activating Token Index: 238

Text #6

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7497. Min Act: -0.1700

Data Index: 8125903 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7444. Min Act: -0.1700

Data Index: 8066660 (Open Web Text)

Max Activating Token Index: 881

Text #8

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7295. Min Act: -0.1700

Data Index: 3088040 (Open Web Text)

Max Activating Token Index: 693

Text #9

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7102. Min Act: -0.1700

Data Index: 2503819 (Open Web Text)

Max Activating Token Index: 658

Text #10

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7234. Min Act: -0.1700

Data Index: 4774310 (Open Web Text)

Max Activating Token Index: 391

Text #11

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7200. Min Act: -0.1700

Data Index: 3533154 (Open Web Text)

Max Activating Token Index: 78

Text #12

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7271. Min Act: -0.1700

Data Index: 3594756 (Open Web Text)

Max Activating Token Index: 269

Text #13

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7285. Min Act: -0.1700

Data Index: 588464 (Open Web Text)

Max Activating Token Index: 619

Text #14

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7108. Min Act: -0.1700

Data Index: 8008786 (Open Web Text)

Max Activating Token Index: 726

Text #15

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7197. Min Act: -0.1700

Data Index: 6593611 (Open Web Text)

Max Activating Token Index: 91

Text #16

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7419. Min Act: -0.1700

Data Index: 6541968 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7167. Min Act: -0.1700

Data Index: 3303605 (Open Web Text)

Max Activating Token Index: 127

Text #18

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7032. Min Act: -0.1700

Data Index: 5422136 (Open Web Text)

Max Activating Token Index: 1007

Text #19

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.7248. Min Act: -0.1700

Data Index: 5695949 (Open Web Text)

Max Activating Token Index: 821