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

Dataset: Open Web Text

Neuron 2218 in Layer 3

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: 3.1298. Min Range: -3.1298

Max Act: 3.1298. Min Act: -0.1700

Data Index: 4949569 (Open Web Text)

Max Activating Token Index: 304

Text #1

Max Range: 3.1298. Min Range: -3.1298

Max Act: 3.1085. Min Act: -0.1700

Data Index: 8349230 (Open Web Text)

Max Activating Token Index: 887

Text #2

Max Range: 3.1298. Min Range: -3.1298

Max Act: 3.0799. Min Act: -0.1700

Data Index: 1734793 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 3.1298. Min Range: -3.1298

Max Act: 3.0735. Min Act: -0.1700

Data Index: 3601127 (Open Web Text)

Max Activating Token Index: 82

Text #4

Max Range: 3.1298. Min Range: -3.1298

Max Act: 3.0195. Min Act: -0.1700

Data Index: 2603357 (Open Web Text)

Max Activating Token Index: 808

Text #5

Max Range: 3.1298. Min Range: -3.1298

Max Act: 3.0030. Min Act: -0.1700

Data Index: 3994903 (Open Web Text)

Max Activating Token Index: 186

Text #6

Max Range: 3.1298. Min Range: -3.1298

Max Act: 3.0286. Min Act: -0.1700

Data Index: 5844743 (Open Web Text)

Max Activating Token Index: 71

Text #7

Max Range: 3.1298. Min Range: -3.1298

Max Act: 3.0269. Min Act: -0.1700

Data Index: 7918383 (Open Web Text)

Max Activating Token Index: 603

Text #8

Max Range: 3.1298. Min Range: -3.1298

Max Act: 3.0167. Min Act: -0.1700

Data Index: 5951607 (Open Web Text)

Max Activating Token Index: 362

Text #9

Max Range: 3.1298. Min Range: -3.1298

Max Act: 3.0037. Min Act: -0.1700

Data Index: 5883416 (Open Web Text)

Max Activating Token Index: 950

Text #10

Max Range: 3.1298. Min Range: -3.1298

Max Act: 2.9936. Min Act: -0.1700

Data Index: 2374737 (Open Web Text)

Max Activating Token Index: 539

Text #11

Max Range: 3.1298. Min Range: -3.1298

Max Act: 2.9504. Min Act: -0.1700

Data Index: 3755889 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 3.1298. Min Range: -3.1298

Max Act: 2.9778. Min Act: -0.1700

Data Index: 4729890 (Open Web Text)

Max Activating Token Index: 142

Text #13

Max Range: 3.1298. Min Range: -3.1298

Max Act: 2.9738. Min Act: -0.1700

Data Index: 7315281 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 3.1298. Min Range: -3.1298

Max Act: 2.9599. Min Act: -0.1700

Data Index: 2437267 (Open Web Text)

Max Activating Token Index: 162

Text #15

Max Range: 3.1298. Min Range: -3.1298

Max Act: 2.9597. Min Act: -0.1700

Data Index: 2555689 (Open Web Text)

Max Activating Token Index: 405

Text #16

Max Range: 3.1298. Min Range: -3.1298

Max Act: 2.9919. Min Act: -0.1700

Data Index: 4502577 (Open Web Text)

Max Activating Token Index: 823

Text #17

Max Range: 3.1298. Min Range: -3.1298

Max Act: 2.9232. Min Act: -0.1700

Data Index: 7449039 (Open Web Text)

Max Activating Token Index: 558

Text #18

Max Range: 3.1298. Min Range: -3.1298

Max Act: 2.9615. Min Act: -0.1700

Data Index: 5630192 (Open Web Text)

Max Activating Token Index: 654

Text #19

Max Range: 3.1298. Min Range: -3.1298

Max Act: 2.9348. Min Act: -0.1700

Data Index: 7301608 (Open Web Text)

Max Activating Token Index: 100