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

Dataset: Open Web Text

Neuron 552 in Layer 5

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: 3.4477. Min Range: -3.4477

Max Act: 3.4477. Min Act: -0.1700

Data Index: 7389865 (Open Web Text)

Max Activating Token Index: 177

Text #1

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3407. Min Act: -0.1700

Data Index: 5023239 (Open Web Text)

Max Activating Token Index: 707

Text #2

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3194. Min Act: -0.1700

Data Index: 2493306 (Open Web Text)

Max Activating Token Index: 680

Text #3

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3055. Min Act: -0.1700

Data Index: 7431903 (Open Web Text)

Max Activating Token Index: 773

Text #4

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2934. Min Act: -0.1700

Data Index: 5477231 (Open Web Text)

Max Activating Token Index: 480

Text #5

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2687. Min Act: -0.1700

Data Index: 7115163 (Open Web Text)

Max Activating Token Index: 456

Text #6

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2405. Min Act: -0.1700

Data Index: 2511924 (Open Web Text)

Max Activating Token Index: 150

Text #7

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2506. Min Act: -0.1700

Data Index: 5789702 (Open Web Text)

Max Activating Token Index: 544

Text #8

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2429. Min Act: -0.1700

Data Index: 2653294 (Open Web Text)

Max Activating Token Index: 268

Text #9

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2548. Min Act: -0.1700

Data Index: 3282228 (Open Web Text)

Max Activating Token Index: 78

Text #10

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2414. Min Act: -0.1700

Data Index: 717554 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2203. Min Act: -0.1700

Data Index: 7642035 (Open Web Text)

Max Activating Token Index: 421

Text #12

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2320. Min Act: -0.1700

Data Index: 8765775 (Open Web Text)

Max Activating Token Index: 53

Text #13

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2398. Min Act: -0.1700

Data Index: 962876 (Open Web Text)

Max Activating Token Index: 104

Text #14

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2160. Min Act: -0.1700

Data Index: 1418742 (Open Web Text)

Max Activating Token Index: 833

Text #15

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2187. Min Act: -0.1700

Data Index: 5459998 (Open Web Text)

Max Activating Token Index: 411

Text #16

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2048. Min Act: -0.1700

Data Index: 6154002 (Open Web Text)

Max Activating Token Index: 280

Text #17

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2089. Min Act: -0.1700

Data Index: 8451024 (Open Web Text)

Max Activating Token Index: 464

Text #18

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2017. Min Act: -0.1700

Data Index: 5123176 (Open Web Text)

Max Activating Token Index: 325

Text #19

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2088. Min Act: -0.1700

Data Index: 1968658 (Open Web Text)

Max Activating Token Index: 398