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

Dataset: Open Web Text

Neuron 2240 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: 2.8198. Min Range: -2.8198

Max Act: 2.8162. Min Act: -0.1700

Data Index: 5355860 (Open Web Text)

Max Activating Token Index: 647

Text #1

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7902. Min Act: -0.1700

Data Index: 198704 (Open Web Text)

Max Activating Token Index: 383

Text #2

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.8198. Min Act: -0.1700

Data Index: 1245454 (Open Web Text)

Max Activating Token Index: 703

Text #3

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.8126. Min Act: -0.1700

Data Index: 7837125 (Open Web Text)

Max Activating Token Index: 853

Text #4

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7779. Min Act: -0.1700

Data Index: 4567675 (Open Web Text)

Max Activating Token Index: 247

Text #5

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7558. Min Act: -0.1700

Data Index: 8751272 (Open Web Text)

Max Activating Token Index: 983

Text #6

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7629. Min Act: -0.1700

Data Index: 2046068 (Open Web Text)

Max Activating Token Index: 1018

Text #7

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7368. Min Act: -0.1700

Data Index: 7461607 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7405. Min Act: -0.1700

Data Index: 3638466 (Open Web Text)

Max Activating Token Index: 722

Text #9

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7575. Min Act: -0.1700

Data Index: 7758920 (Open Web Text)

Max Activating Token Index: 846

Text #10

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7369. Min Act: -0.1700

Data Index: 6882995 (Open Web Text)

Max Activating Token Index: 155

Text #11

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7170. Min Act: -0.1700

Data Index: 2764720 (Open Web Text)

Max Activating Token Index: 874

Text #12

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7201. Min Act: -0.1700

Data Index: 3948802 (Open Web Text)

Max Activating Token Index: 399

Text #13

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7310. Min Act: -0.1700

Data Index: 107485 (Open Web Text)

Max Activating Token Index: 862

Text #14

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7437. Min Act: -0.1700

Data Index: 2060508 (Open Web Text)

Max Activating Token Index: 86

Text #15

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7098. Min Act: -0.1700

Data Index: 3464605 (Open Web Text)

Max Activating Token Index: 812

Text #16

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7178. Min Act: -0.1700

Data Index: 2279775 (Open Web Text)

Max Activating Token Index: 155

Text #17

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7014. Min Act: -0.1700

Data Index: 8142627 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7005. Min Act: -0.1700

Data Index: 6925545 (Open Web Text)

Max Activating Token Index: 943

Text #19

Max Range: 2.8198. Min Range: -2.8198

Max Act: 2.7083. Min Act: -0.1700

Data Index: 7040074 (Open Web Text)

Max Activating Token Index: 879