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

Dataset: Open Web Text

Neuron 996 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: 3.7226. Min Range: -3.7226

Max Act: 3.7226. Min Act: -0.1700

Data Index: 6018819 (Open Web Text)

Max Activating Token Index: 232

Text #1

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.6992. Min Act: -0.1700

Data Index: 2650668 (Open Web Text)

Max Activating Token Index: 474

Text #2

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5844. Min Act: -0.1700

Data Index: 259607 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5811. Min Act: -0.1700

Data Index: 2280065 (Open Web Text)

Max Activating Token Index: 377

Text #4

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5694. Min Act: -0.1700

Data Index: 7369408 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5895. Min Act: -0.1700

Data Index: 6231860 (Open Web Text)

Max Activating Token Index: 525

Text #6

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5357. Min Act: -0.1700

Data Index: 5266408 (Open Web Text)

Max Activating Token Index: 514

Text #7

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5167. Min Act: -0.1700

Data Index: 6608387 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5261. Min Act: -0.1700

Data Index: 5564930 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5384. Min Act: -0.1700

Data Index: 4987005 (Open Web Text)

Max Activating Token Index: 756

Text #10

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5130. Min Act: -0.1700

Data Index: 5955200 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5206. Min Act: -0.1700

Data Index: 3695560 (Open Web Text)

Max Activating Token Index: 865

Text #12

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5100. Min Act: -0.1700

Data Index: 2338541 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5013. Min Act: -0.1700

Data Index: 8417127 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5108. Min Act: -0.1700

Data Index: 5993693 (Open Web Text)

Max Activating Token Index: 408

Text #15

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.4586. Min Act: -0.1700

Data Index: 7808919 (Open Web Text)

Max Activating Token Index: 763

Text #16

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.5156. Min Act: -0.1700

Data Index: 5819547 (Open Web Text)

Max Activating Token Index: 593

Text #17

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.4448. Min Act: -0.1700

Data Index: 4723085 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.4928. Min Act: -0.1700

Data Index: 7881455 (Open Web Text)

Max Activating Token Index: 568

Text #19

Max Range: 3.7226. Min Range: -3.7226

Max Act: 3.4449. Min Act: -0.1700

Data Index: 6525912 (Open Web Text)

Max Activating Token Index: 761