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

Dataset: Open Web Text

Neuron 2170 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: 3.8187. Min Range: -3.8187

Max Act: 3.8187. Min Act: -0.1700

Data Index: 259699 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.7331. Min Act: -0.1700

Data Index: 6966502 (Open Web Text)

Max Activating Token Index: 449

Text #2

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.7095. Min Act: -0.1700

Data Index: 2659701 (Open Web Text)

Max Activating Token Index: 186

Text #3

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6818. Min Act: -0.1700

Data Index: 3034628 (Open Web Text)

Max Activating Token Index: 97

Text #4

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6771. Min Act: -0.1700

Data Index: 8161707 (Open Web Text)

Max Activating Token Index: 500

Text #5

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6440. Min Act: -0.1700

Data Index: 6831459 (Open Web Text)

Max Activating Token Index: 488

Text #6

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6339. Min Act: -0.1700

Data Index: 5494927 (Open Web Text)

Max Activating Token Index: 773

Text #7

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6415. Min Act: -0.1700

Data Index: 5405150 (Open Web Text)

Max Activating Token Index: 273

Text #8

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6662. Min Act: -0.1700

Data Index: 8576813 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.5527. Min Act: -0.1700

Data Index: 262100 (Open Web Text)

Max Activating Token Index: 790

Text #10

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6088. Min Act: -0.1700

Data Index: 8539577 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.5405. Min Act: -0.1700

Data Index: 3994161 (Open Web Text)

Max Activating Token Index: 703

Text #12

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.5292. Min Act: -0.1700

Data Index: 2617097 (Open Web Text)

Max Activating Token Index: 194

Text #13

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.5346. Min Act: -0.1700

Data Index: 5143746 (Open Web Text)

Max Activating Token Index: 997

Text #14

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.5429. Min Act: -0.1700

Data Index: 8053632 (Open Web Text)

Max Activating Token Index: 276

Text #15

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.5220. Min Act: -0.1700

Data Index: 1447822 (Open Web Text)

Max Activating Token Index: 718

Text #16

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.4717. Min Act: -0.1700

Data Index: 132445 (Open Web Text)

Max Activating Token Index: 623

Text #17

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.5679. Min Act: -0.1700

Data Index: 3065994 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.5680. Min Act: -0.1700

Data Index: 2275926 (Open Web Text)

Max Activating Token Index: 284

Text #19

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.5468. Min Act: -0.1700

Data Index: 423871 (Open Web Text)

Max Activating Token Index: 458