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

Dataset: Open Web Text

Neuron 2277 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: 2.7202. Min Range: -2.7202

Max Act: 2.7202. Min Act: -0.1700

Data Index: 7676964 (Open Web Text)

Max Activating Token Index: 617

Text #1

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6980. Min Act: -0.1700

Data Index: 3340614 (Open Web Text)

Max Activating Token Index: 187

Text #2

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6560. Min Act: -0.1700

Data Index: 3270475 (Open Web Text)

Max Activating Token Index: 580

Text #3

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6538. Min Act: -0.1700

Data Index: 2011901 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6580. Min Act: -0.1700

Data Index: 4651857 (Open Web Text)

Max Activating Token Index: 95

Text #5

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6370. Min Act: -0.1700

Data Index: 264110 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6360. Min Act: -0.1700

Data Index: 3452900 (Open Web Text)

Max Activating Token Index: 944

Text #7

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6349. Min Act: -0.1700

Data Index: 2927771 (Open Web Text)

Max Activating Token Index: 50

Text #8

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6186. Min Act: -0.1700

Data Index: 2608178 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6166. Min Act: -0.1700

Data Index: 5594804 (Open Web Text)

Max Activating Token Index: 103

Text #10

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.5861. Min Act: -0.1700

Data Index: 6760609 (Open Web Text)

Max Activating Token Index: 538

Text #11

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6199. Min Act: -0.1700

Data Index: 3746667 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6103. Min Act: -0.1700

Data Index: 3043450 (Open Web Text)

Max Activating Token Index: 144

Text #13

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6034. Min Act: -0.1700

Data Index: 7024401 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6284. Min Act: -0.1700

Data Index: 2128487 (Open Web Text)

Max Activating Token Index: 182

Text #15

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6186. Min Act: -0.1700

Data Index: 1143356 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6186. Min Act: -0.1700

Data Index: 7908665 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6186. Min Act: -0.1700

Data Index: 4569081 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6186. Min Act: -0.1700

Data Index: 215546 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.7202. Min Range: -2.7202

Max Act: 2.6150. Min Act: -0.1700

Data Index: 3032283 (Open Web Text)

Max Activating Token Index: 403