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

Dataset: Open Web Text

Neuron 527 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: 3.0465. Min Range: -3.0465

Max Act: 3.0465. Min Act: -0.1700

Data Index: 8497315 (Open Web Text)

Max Activating Token Index: 950

Text #1

Max Range: 3.0465. Min Range: -3.0465

Max Act: 3.0031. Min Act: -0.1700

Data Index: 1147300 (Open Web Text)

Max Activating Token Index: 423

Text #2

Max Range: 3.0465. Min Range: -3.0465

Max Act: 3.0130. Min Act: -0.1700

Data Index: 4496125 (Open Web Text)

Max Activating Token Index: 327

Text #3

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.9732. Min Act: -0.1700

Data Index: 432563 (Open Web Text)

Max Activating Token Index: 205

Text #4

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.9488. Min Act: -0.1700

Data Index: 802792 (Open Web Text)

Max Activating Token Index: 878

Text #5

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.9213. Min Act: -0.1700

Data Index: 1447354 (Open Web Text)

Max Activating Token Index: 149

Text #6

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.9177. Min Act: -0.1700

Data Index: 5350679 (Open Web Text)

Max Activating Token Index: 482

Text #7

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.9141. Min Act: -0.1700

Data Index: 6210327 (Open Web Text)

Max Activating Token Index: 921

Text #8

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.9093. Min Act: -0.1700

Data Index: 6677286 (Open Web Text)

Max Activating Token Index: 295

Text #9

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.9077. Min Act: -0.1700

Data Index: 344325 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.9025. Min Act: -0.1700

Data Index: 2583864 (Open Web Text)

Max Activating Token Index: 249

Text #11

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.8964. Min Act: -0.1700

Data Index: 1222832 (Open Web Text)

Max Activating Token Index: 295

Text #12

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.8767. Min Act: -0.1700

Data Index: 7862395 (Open Web Text)

Max Activating Token Index: 636

Text #13

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.8533. Min Act: -0.1700

Data Index: 3019924 (Open Web Text)

Max Activating Token Index: 784

Text #14

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.8558. Min Act: -0.1700

Data Index: 4789115 (Open Web Text)

Max Activating Token Index: 186

Text #15

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.8394. Min Act: -0.1700

Data Index: 736157 (Open Web Text)

Max Activating Token Index: 998

Text #16

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.8225. Min Act: -0.1700

Data Index: 6349781 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.8330. Min Act: -0.1700

Data Index: 3219258 (Open Web Text)

Max Activating Token Index: 890

Text #18

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.8290. Min Act: -0.1700

Data Index: 1068596 (Open Web Text)

Max Activating Token Index: 351

Text #19

Max Range: 3.0465. Min Range: -3.0465

Max Act: 2.8330. Min Act: -0.1700

Data Index: 385482 (Open Web Text)

Max Activating Token Index: 979