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

Dataset: Open Web Text

Neuron 1365 in Layer 2

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: 3.9761. Min Range: -3.9761

Max Act: 3.9761. Min Act: -0.1700

Data Index: 8513166 (Open Web Text)

Max Activating Token Index: 932

Text #1

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.8130. Min Act: -0.1700

Data Index: 5259207 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.8338. Min Act: -0.1700

Data Index: 5215261 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.7645. Min Act: -0.1700

Data Index: 3479373 (Open Web Text)

Max Activating Token Index: 128

Text #4

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.7777. Min Act: -0.1700

Data Index: 4562497 (Open Web Text)

Max Activating Token Index: 384

Text #5

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.7472. Min Act: -0.1700

Data Index: 880854 (Open Web Text)

Max Activating Token Index: 109

Text #6

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.7604. Min Act: -0.1700

Data Index: 2217020 (Open Web Text)

Max Activating Token Index: 736

Text #7

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.8075. Min Act: -0.1700

Data Index: 6118330 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.7433. Min Act: -0.1700

Data Index: 7869991 (Open Web Text)

Max Activating Token Index: 136

Text #9

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.6933. Min Act: -0.1700

Data Index: 7870004 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.7467. Min Act: -0.1700

Data Index: 3630577 (Open Web Text)

Max Activating Token Index: 244

Text #11

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.6953. Min Act: -0.1700

Data Index: 7008371 (Open Web Text)

Max Activating Token Index: 214

Text #12

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.7001. Min Act: -0.1700

Data Index: 7590003 (Open Web Text)

Max Activating Token Index: 941

Text #13

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.7138. Min Act: -0.1700

Data Index: 6214 (Open Web Text)

Max Activating Token Index: 538

Text #14

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.6822. Min Act: -0.1700

Data Index: 4650469 (Open Web Text)

Max Activating Token Index: 947

Text #15

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.6598. Min Act: -0.1700

Data Index: 1935894 (Open Web Text)

Max Activating Token Index: 884

Text #16

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.6772. Min Act: -0.1700

Data Index: 1234292 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.6715. Min Act: -0.1700

Data Index: 1746338 (Open Web Text)

Max Activating Token Index: 426

Text #18

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.6565. Min Act: -0.1700

Data Index: 5926602 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.6634. Min Act: -0.1700

Data Index: 8320882 (Open Web Text)

Max Activating Token Index: 420