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

Dataset: Open Web Text

Neuron 883 in Layer 0

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: 3.1215. Min Range: -3.1215

Max Act: 3.1215. Min Act: -0.1700

Data Index: 8409977 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.1084. Min Act: -0.1700

Data Index: 332971 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.1000. Min Act: -0.1700

Data Index: 362666 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0473. Min Act: -0.1700

Data Index: 5009297 (Open Web Text)

Max Activating Token Index: 379

Text #4

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0128. Min Act: -0.1700

Data Index: 8750725 (Open Web Text)

Max Activating Token Index: 343

Text #5

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0099. Min Act: -0.1700

Data Index: 8661162 (Open Web Text)

Max Activating Token Index: 398

Text #6

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0135. Min Act: -0.1700

Data Index: 5756472 (Open Web Text)

Max Activating Token Index: 807

Text #7

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0042. Min Act: -0.1700

Data Index: 7081844 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9843. Min Act: -0.1700

Data Index: 2117896 (Open Web Text)

Max Activating Token Index: 772

Text #9

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9914. Min Act: -0.1700

Data Index: 2129214 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9925. Min Act: -0.1700

Data Index: 5336011 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9908. Min Act: -0.1700

Data Index: 519463 (Open Web Text)

Max Activating Token Index: 547

Text #12

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9766. Min Act: -0.1700

Data Index: 2479281 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9771. Min Act: -0.1700

Data Index: 8388790 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9587. Min Act: -0.1700

Data Index: 5027532 (Open Web Text)

Max Activating Token Index: 62

Text #15

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9700. Min Act: -0.1700

Data Index: 8443217 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9680. Min Act: -0.1700

Data Index: 3410089 (Open Web Text)

Max Activating Token Index: 177

Text #17

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9684. Min Act: -0.1700

Data Index: 7978419 (Open Web Text)

Max Activating Token Index: 56

Text #18

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9717. Min Act: -0.1700

Data Index: 3022309 (Open Web Text)

Max Activating Token Index: 77

Text #19

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9650. Min Act: -0.1700

Data Index: 1839395 (Open Web Text)

Max Activating Token Index: 355