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

Dataset: Open Web Text

Neuron 2259 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: 4.2858. Min Range: -4.2858

Max Act: 4.2858. Min Act: -0.1700

Data Index: 5166533 (Open Web Text)

Max Activating Token Index: 857

Text #1

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.2363. Min Act: -0.1700

Data Index: 1327228 (Open Web Text)

Max Activating Token Index: 1012

Text #2

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.2205. Min Act: -0.1700

Data Index: 2429867 (Open Web Text)

Max Activating Token Index: 872

Text #3

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.1839. Min Act: -0.1700

Data Index: 51679 (Open Web Text)

Max Activating Token Index: 585

Text #4

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.1850. Min Act: -0.1700

Data Index: 5050689 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.1678. Min Act: -0.1700

Data Index: 4462616 (Open Web Text)

Max Activating Token Index: 708

Text #6

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.1232. Min Act: -0.1700

Data Index: 6954123 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.1157. Min Act: -0.1700

Data Index: 7464997 (Open Web Text)

Max Activating Token Index: 983

Text #8

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.1234. Min Act: -0.1700

Data Index: 1914042 (Open Web Text)

Max Activating Token Index: 357

Text #9

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0320. Min Act: -0.1700

Data Index: 4298604 (Open Web Text)

Max Activating Token Index: 420

Text #10

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0973. Min Act: -0.1700

Data Index: 7484078 (Open Web Text)

Max Activating Token Index: 44

Text #11

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0584. Min Act: -0.1700

Data Index: 4646750 (Open Web Text)

Max Activating Token Index: 660

Text #12

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0734. Min Act: -0.1700

Data Index: 1817670 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0656. Min Act: -0.1700

Data Index: 173063 (Open Web Text)

Max Activating Token Index: 118

Text #14

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0489. Min Act: -0.1700

Data Index: 2787668 (Open Web Text)

Max Activating Token Index: 464

Text #15

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0383. Min Act: -0.1700

Data Index: 4216826 (Open Web Text)

Max Activating Token Index: 566

Text #16

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0600. Min Act: -0.1700

Data Index: 6408828 (Open Web Text)

Max Activating Token Index: 362

Text #17

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0678. Min Act: -0.1700

Data Index: 6880737 (Open Web Text)

Max Activating Token Index: 77

Text #18

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0627. Min Act: -0.1700

Data Index: 770057 (Open Web Text)

Max Activating Token Index: 454

Text #19

Max Range: 4.2858. Min Range: -4.2858

Max Act: 4.0275. Min Act: -0.1700

Data Index: 7609414 (Open Web Text)

Max Activating Token Index: 949