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

Dataset: Open Web Text

Neuron 881 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: 3.7152. Min Range: -3.7152

Max Act: 3.7152. Min Act: -0.1700

Data Index: 7991238 (Open Web Text)

Max Activating Token Index: 418

Text #1

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6930. Min Act: -0.1700

Data Index: 4920554 (Open Web Text)

Max Activating Token Index: 465

Text #2

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6830. Min Act: -0.1700

Data Index: 2432927 (Open Web Text)

Max Activating Token Index: 57

Text #3

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6500. Min Act: -0.1700

Data Index: 5553278 (Open Web Text)

Max Activating Token Index: 952

Text #4

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6586. Min Act: -0.1700

Data Index: 8114544 (Open Web Text)

Max Activating Token Index: 613

Text #5

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6811. Min Act: -0.1700

Data Index: 5289483 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6523. Min Act: -0.1700

Data Index: 1825315 (Open Web Text)

Max Activating Token Index: 34

Text #7

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6644. Min Act: -0.1700

Data Index: 3446850 (Open Web Text)

Max Activating Token Index: 248

Text #8

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6514. Min Act: -0.1700

Data Index: 2051554 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6296. Min Act: -0.1700

Data Index: 560820 (Open Web Text)

Max Activating Token Index: 227

Text #10

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6397. Min Act: -0.1700

Data Index: 7153370 (Open Web Text)

Max Activating Token Index: 477

Text #11

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6467. Min Act: -0.1700

Data Index: 3775439 (Open Web Text)

Max Activating Token Index: 614

Text #12

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6091. Min Act: -0.1700

Data Index: 857439 (Open Web Text)

Max Activating Token Index: 81

Text #13

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6015. Min Act: -0.1700

Data Index: 7001158 (Open Web Text)

Max Activating Token Index: 937

Text #14

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5909. Min Act: -0.1700

Data Index: 7896449 (Open Web Text)

Max Activating Token Index: 910

Text #15

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5868. Min Act: -0.1700

Data Index: 7507998 (Open Web Text)

Max Activating Token Index: 143

Text #16

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5823. Min Act: -0.1700

Data Index: 8413048 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.6039. Min Act: -0.1700

Data Index: 2307521 (Open Web Text)

Max Activating Token Index: 563

Text #18

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5819. Min Act: -0.1700

Data Index: 7657482 (Open Web Text)

Max Activating Token Index: 278

Text #19

Max Range: 3.7152. Min Range: -3.7152

Max Act: 3.5924. Min Act: -0.1700

Data Index: 3778922 (Open Web Text)

Max Activating Token Index: 146