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

Dataset: Open Web Text

Neuron 2834 in Layer 4

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: 3.9463. Min Range: -3.9463

Max Act: 3.9463. Min Act: -0.1700

Data Index: 2484445 (Open Web Text)

Max Activating Token Index: 845

Text #1

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.8125. Min Act: -0.1700

Data Index: 3132159 (Open Web Text)

Max Activating Token Index: 461

Text #2

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7777. Min Act: -0.1700

Data Index: 2687423 (Open Web Text)

Max Activating Token Index: 799

Text #3

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7289. Min Act: -0.1700

Data Index: 8588451 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7105. Min Act: -0.1700

Data Index: 5823365 (Open Web Text)

Max Activating Token Index: 822

Text #5

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7003. Min Act: -0.1700

Data Index: 2753955 (Open Web Text)

Max Activating Token Index: 537

Text #6

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.6871. Min Act: -0.1700

Data Index: 347793 (Open Web Text)

Max Activating Token Index: 1010

Text #7

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7013. Min Act: -0.1700

Data Index: 5462384 (Open Web Text)

Max Activating Token Index: 958

Text #8

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.6749. Min Act: -0.1700

Data Index: 5109453 (Open Web Text)

Max Activating Token Index: 875

Text #9

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.6594. Min Act: -0.1700

Data Index: 5273121 (Open Web Text)

Max Activating Token Index: 233

Text #10

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.5796. Min Act: -0.1700

Data Index: 456549 (Open Web Text)

Max Activating Token Index: 635

Text #11

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.6501. Min Act: -0.1700

Data Index: 779419 (Open Web Text)

Max Activating Token Index: 643

Text #12

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.6336. Min Act: -0.1700

Data Index: 3855013 (Open Web Text)

Max Activating Token Index: 151

Text #13

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.6078. Min Act: -0.1700

Data Index: 5095504 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.6174. Min Act: -0.1700

Data Index: 3417941 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.6324. Min Act: -0.1700

Data Index: 91698 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.5697. Min Act: -0.1700

Data Index: 4400820 (Open Web Text)

Max Activating Token Index: 633

Text #17

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.5981. Min Act: -0.1700

Data Index: 382305 (Open Web Text)

Max Activating Token Index: 318

Text #18

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.5824. Min Act: -0.1700

Data Index: 5375270 (Open Web Text)

Max Activating Token Index: 889

Text #19

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.5972. Min Act: -0.1700

Data Index: 5686523 (Open Web Text)

Max Activating Token Index: 604