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

Dataset: Open Web Text

Neuron 1841 in Layer 3

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: 3.1604. Min Range: -3.1604

Max Act: 3.1594. Min Act: -0.1700

Data Index: 4793285 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.1353. Min Act: -0.1700

Data Index: 2150244 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.1461. Min Act: -0.1700

Data Index: 4725514 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.1604. Min Act: -0.1700

Data Index: 2975482 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.1205. Min Act: -0.1700

Data Index: 4817199 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.1095. Min Act: -0.1700

Data Index: 8427699 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.1101. Min Act: -0.1700

Data Index: 1505300 (Open Web Text)

Max Activating Token Index: 939

Text #7

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.1095. Min Act: -0.1700

Data Index: 93221 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0842. Min Act: -0.1700

Data Index: 8334284 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0567. Min Act: -0.1700

Data Index: 856208 (Open Web Text)

Max Activating Token Index: 990

Text #10

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0885. Min Act: -0.1700

Data Index: 13726 (Open Web Text)

Max Activating Token Index: 856

Text #11

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0748. Min Act: -0.1700

Data Index: 8626517 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0969. Min Act: -0.1700

Data Index: 8476699 (Open Web Text)

Max Activating Token Index: 987

Text #13

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0487. Min Act: -0.1700

Data Index: 4007450 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0464. Min Act: -0.1700

Data Index: 7971149 (Open Web Text)

Max Activating Token Index: 980

Text #15

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0514. Min Act: -0.1700

Data Index: 7142011 (Open Web Text)

Max Activating Token Index: 862

Text #16

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0543. Min Act: -0.1700

Data Index: 915714 (Open Web Text)

Max Activating Token Index: 465

Text #17

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0213. Min Act: -0.1700

Data Index: 5455314 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0512. Min Act: -0.1700

Data Index: 4616537 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 3.1604. Min Range: -3.1604

Max Act: 3.0407. Min Act: -0.1700

Data Index: 915722 (Open Web Text)

Max Activating Token Index: 686