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

Dataset: Open Web Text

Neuron 127 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: 3.3990. Min Range: -3.3990

Max Act: 3.3990. Min Act: -0.1700

Data Index: 4492341 (Open Web Text)

Max Activating Token Index: 343

Text #1

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.1516. Min Act: -0.1700

Data Index: 3998636 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.1150. Min Act: -0.1700

Data Index: 2060996 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.1019. Min Act: -0.1700

Data Index: 4158029 (Open Web Text)

Max Activating Token Index: 943

Text #4

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.0841. Min Act: -0.1700

Data Index: 970104 (Open Web Text)

Max Activating Token Index: 264

Text #5

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.0712. Min Act: -0.1700

Data Index: 5243180 (Open Web Text)

Max Activating Token Index: 681

Text #6

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.0520. Min Act: -0.1700

Data Index: 7084330 (Open Web Text)

Max Activating Token Index: 559

Text #7

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.0337. Min Act: -0.1700

Data Index: 7943369 (Open Web Text)

Max Activating Token Index: 811

Text #8

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.0301. Min Act: -0.1700

Data Index: 6577803 (Open Web Text)

Max Activating Token Index: 1016

Text #9

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.0376. Min Act: -0.1700

Data Index: 1083572 (Open Web Text)

Max Activating Token Index: 262

Text #10

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.0483. Min Act: -0.1700

Data Index: 3701174 (Open Web Text)

Max Activating Token Index: 102

Text #11

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.0208. Min Act: -0.1700

Data Index: 2712357 (Open Web Text)

Max Activating Token Index: 646

Text #12

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.0042. Min Act: -0.1700

Data Index: 7637248 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 3.3990. Min Range: -3.3990

Max Act: 3.0311. Min Act: -0.1700

Data Index: 4985262 (Open Web Text)

Max Activating Token Index: 996

Text #14

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.9899. Min Act: -0.1700

Data Index: 6089433 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.9864. Min Act: -0.1700

Data Index: 2890599 (Open Web Text)

Max Activating Token Index: 117

Text #16

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.9748. Min Act: -0.1700

Data Index: 6208242 (Open Web Text)

Max Activating Token Index: 327

Text #17

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.9963. Min Act: -0.1700

Data Index: 5955526 (Open Web Text)

Max Activating Token Index: 872

Text #18

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.9768. Min Act: -0.1700

Data Index: 6619100 (Open Web Text)

Max Activating Token Index: 721

Text #19

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.9580. Min Act: -0.1700

Data Index: 3085370 (Open Web Text)

Max Activating Token Index: 426