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

Dataset: Open Web Text

Neuron 429 in Layer 1

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: 2.9163. Min Range: -2.9163

Max Act: 2.9163. Min Act: -0.1700

Data Index: 7567165 (Open Web Text)

Max Activating Token Index: 214

Text #1

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.8854. Min Act: -0.1700

Data Index: 4957822 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.8181. Min Act: -0.1699

Data Index: 5678136 (Open Web Text)

Max Activating Token Index: 85

Text #3

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.8050. Min Act: -0.1700

Data Index: 5288531 (Open Web Text)

Max Activating Token Index: 725

Text #4

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.7309. Min Act: -0.1700

Data Index: 1543739 (Open Web Text)

Max Activating Token Index: 244

Text #5

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.7052. Min Act: -0.1700

Data Index: 5026044 (Open Web Text)

Max Activating Token Index: 841

Text #6

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.7569. Min Act: -0.1700

Data Index: 8330954 (Open Web Text)

Max Activating Token Index: 650

Text #7

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.7033. Min Act: -0.1700

Data Index: 5685418 (Open Web Text)

Max Activating Token Index: 872

Text #8

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.6324. Min Act: -0.1695

Data Index: 4277101 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.6435. Min Act: -0.1700

Data Index: 345154 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.6487. Min Act: -0.1700

Data Index: 360977 (Open Web Text)

Max Activating Token Index: 585

Text #11

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.6148. Min Act: -0.1700

Data Index: 5245915 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.6387. Min Act: -0.1700

Data Index: 5345453 (Open Web Text)

Max Activating Token Index: 979

Text #13

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.6051. Min Act: -0.1700

Data Index: 2520225 (Open Web Text)

Max Activating Token Index: 769

Text #14

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.5823. Min Act: -0.1700

Data Index: 3461961 (Open Web Text)

Max Activating Token Index: 123

Text #15

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.6024. Min Act: -0.1700

Data Index: 1044452 (Open Web Text)

Max Activating Token Index: 432

Text #16

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.5917. Min Act: -0.1700

Data Index: 2834970 (Open Web Text)

Max Activating Token Index: 940

Text #17

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.5645. Min Act: -0.1700

Data Index: 6463085 (Open Web Text)

Max Activating Token Index: 432

Text #18

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.5900. Min Act: -0.1700

Data Index: 8716523 (Open Web Text)

Max Activating Token Index: 511

Text #19

Max Range: 2.9163. Min Range: -2.9163

Max Act: 2.5624. Min Act: -0.1694

Data Index: 7785143 (Open Web Text)

Max Activating Token Index: 986