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

Dataset: Open Web Text

Neuron 2943 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: 4.6592. Min Range: -4.6592

Max Act: 4.6592. Min Act: -0.1700

Data Index: 1840452 (Open Web Text)

Max Activating Token Index: 156

Text #1

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.6341. Min Act: -0.1700

Data Index: 3411070 (Open Web Text)

Max Activating Token Index: 654

Text #2

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.6253. Min Act: -0.1700

Data Index: 1979467 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.5684. Min Act: -0.1700

Data Index: 1830886 (Open Web Text)

Max Activating Token Index: 421

Text #4

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.5516. Min Act: -0.1700

Data Index: 6169873 (Open Web Text)

Max Activating Token Index: 471

Text #5

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.5069. Min Act: -0.1700

Data Index: 1048551 (Open Web Text)

Max Activating Token Index: 570

Text #6

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.4678. Min Act: -0.1700

Data Index: 5136429 (Open Web Text)

Max Activating Token Index: 790

Text #7

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.4371. Min Act: -0.1700

Data Index: 1331801 (Open Web Text)

Max Activating Token Index: 179

Text #8

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.4044. Min Act: -0.1700

Data Index: 4553162 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.4318. Min Act: -0.1700

Data Index: 1911459 (Open Web Text)

Max Activating Token Index: 231

Text #10

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.4163. Min Act: -0.1700

Data Index: 859477 (Open Web Text)

Max Activating Token Index: 131

Text #11

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.4031. Min Act: -0.1700

Data Index: 5969899 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.4086. Min Act: -0.1700

Data Index: 4282188 (Open Web Text)

Max Activating Token Index: 810

Text #13

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.3720. Min Act: -0.1700

Data Index: 8292039 (Open Web Text)

Max Activating Token Index: 844

Text #14

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.3748. Min Act: -0.1700

Data Index: 2821539 (Open Web Text)

Max Activating Token Index: 622

Text #15

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.3933. Min Act: -0.1700

Data Index: 7696672 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.3998. Min Act: -0.1700

Data Index: 5695659 (Open Web Text)

Max Activating Token Index: 923

Text #17

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.3226. Min Act: -0.1700

Data Index: 6434614 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.3447. Min Act: -0.1700

Data Index: 7130071 (Open Web Text)

Max Activating Token Index: 101

Text #19

Max Range: 4.6592. Min Range: -4.6592

Max Act: 4.3658. Min Act: -0.1700

Data Index: 3926637 (Open Web Text)

Max Activating Token Index: 593