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

Dataset: Open Web Text

Neuron 814 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: 1.9150. Min Range: -1.9150

Max Act: 1.9090. Min Act: -0.1700

Data Index: 338313 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.9150. Min Act: -0.1700

Data Index: 2999626 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8846. Min Act: -0.1700

Data Index: 8383538 (Open Web Text)

Max Activating Token Index: 202

Text #3

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8838. Min Act: -0.1700

Data Index: 2592194 (Open Web Text)

Max Activating Token Index: 371

Text #4

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8803. Min Act: -0.1700

Data Index: 2267198 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8392. Min Act: -0.1700

Data Index: 5994438 (Open Web Text)

Max Activating Token Index: 105

Text #6

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8307. Min Act: -0.1700

Data Index: 6024234 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8156. Min Act: -0.1700

Data Index: 7723087 (Open Web Text)

Max Activating Token Index: 561

Text #8

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8183. Min Act: -0.1700

Data Index: 5396187 (Open Web Text)

Max Activating Token Index: 147

Text #9

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8180. Min Act: -0.1700

Data Index: 3373824 (Open Web Text)

Max Activating Token Index: 209

Text #10

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8012. Min Act: -0.1700

Data Index: 6652240 (Open Web Text)

Max Activating Token Index: 525

Text #11

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8098. Min Act: -0.1700

Data Index: 6788590 (Open Web Text)

Max Activating Token Index: 510

Text #12

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8048. Min Act: -0.1700

Data Index: 4201537 (Open Web Text)

Max Activating Token Index: 103

Text #13

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8049. Min Act: -0.1700

Data Index: 3281987 (Open Web Text)

Max Activating Token Index: 272

Text #14

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8068. Min Act: -0.1700

Data Index: 7313783 (Open Web Text)

Max Activating Token Index: 585

Text #15

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.7917. Min Act: -0.1700

Data Index: 8143991 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.7809. Min Act: -0.1700

Data Index: 3450097 (Open Web Text)

Max Activating Token Index: 845

Text #17

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.7898. Min Act: -0.1700

Data Index: 7521554 (Open Web Text)

Max Activating Token Index: 258

Text #18

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.7945. Min Act: -0.1700

Data Index: 4239536 (Open Web Text)

Max Activating Token Index: 53

Text #19

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.7914. Min Act: -0.1700

Data Index: 459014 (Open Web Text)

Max Activating Token Index: 142