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

Dataset: Open Web Text

Neuron 2703 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: 3.1405. Min Range: -3.1405

Max Act: 3.1405. Min Act: -0.1700

Data Index: 320443 (Open Web Text)

Max Activating Token Index: 329

Text #1

Max Range: 3.1405. Min Range: -3.1405

Max Act: 3.1374. Min Act: -0.1700

Data Index: 5733348 (Open Web Text)

Max Activating Token Index: 43

Text #2

Max Range: 3.1405. Min Range: -3.1405

Max Act: 3.0127. Min Act: -0.1700

Data Index: 84783 (Open Web Text)

Max Activating Token Index: 736

Text #3

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9774. Min Act: -0.1700

Data Index: 2864753 (Open Web Text)

Max Activating Token Index: 952

Text #4

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9747. Min Act: -0.1700

Data Index: 3128303 (Open Web Text)

Max Activating Token Index: 53

Text #5

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9567. Min Act: -0.1700

Data Index: 8310406 (Open Web Text)

Max Activating Token Index: 655

Text #6

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9625. Min Act: -0.1700

Data Index: 4341558 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9276. Min Act: -0.1700

Data Index: 4047427 (Open Web Text)

Max Activating Token Index: 334

Text #8

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9293. Min Act: -0.1700

Data Index: 3820224 (Open Web Text)

Max Activating Token Index: 612

Text #9

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9024. Min Act: -0.1700

Data Index: 234551 (Open Web Text)

Max Activating Token Index: 594

Text #10

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9124. Min Act: -0.1700

Data Index: 5943643 (Open Web Text)

Max Activating Token Index: 529

Text #11

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9315. Min Act: -0.1700

Data Index: 2799245 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9043. Min Act: -0.1700

Data Index: 1527055 (Open Web Text)

Max Activating Token Index: 441

Text #13

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9257. Min Act: -0.1700

Data Index: 6828203 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9037. Min Act: -0.1700

Data Index: 739168 (Open Web Text)

Max Activating Token Index: 800

Text #15

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8846. Min Act: -0.1700

Data Index: 2406575 (Open Web Text)

Max Activating Token Index: 496

Text #16

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9153. Min Act: -0.1700

Data Index: 7854768 (Open Web Text)

Max Activating Token Index: 800

Text #17

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9093. Min Act: -0.1700

Data Index: 4562317 (Open Web Text)

Max Activating Token Index: 747

Text #18

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8981. Min Act: -0.1700

Data Index: 5324228 (Open Web Text)

Max Activating Token Index: 450

Text #19

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9084. Min Act: -0.1700

Data Index: 2049901 (Open Web Text)

Max Activating Token Index: 588