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

Dataset: Open Web Text

Neuron 2236 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: 3.2116. Min Range: -3.2116

Max Act: 3.2116. Min Act: -0.1700

Data Index: 626554 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.1385. Min Act: -0.1700

Data Index: 7936751 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.1307. Min Act: -0.1700

Data Index: 4943623 (Open Web Text)

Max Activating Token Index: 547

Text #3

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0958. Min Act: -0.1700

Data Index: 2363155 (Open Web Text)

Max Activating Token Index: 537

Text #4

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0831. Min Act: -0.1700

Data Index: 867993 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0717. Min Act: -0.1700

Data Index: 4775683 (Open Web Text)

Max Activating Token Index: 337

Text #6

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0432. Min Act: -0.1700

Data Index: 3493469 (Open Web Text)

Max Activating Token Index: 123

Text #7

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0200. Min Act: -0.1700

Data Index: 4300800 (Open Web Text)

Max Activating Token Index: 334

Text #8

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0323. Min Act: -0.1700

Data Index: 7928526 (Open Web Text)

Max Activating Token Index: 436

Text #9

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0231. Min Act: -0.1700

Data Index: 5731388 (Open Web Text)

Max Activating Token Index: 32

Text #10

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0021. Min Act: -0.1700

Data Index: 3423828 (Open Web Text)

Max Activating Token Index: 95

Text #11

Max Range: 3.2116. Min Range: -3.2116

Max Act: 2.9896. Min Act: -0.1700

Data Index: 8564270 (Open Web Text)

Max Activating Token Index: 164

Text #12

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0045. Min Act: -0.1700

Data Index: 4862365 (Open Web Text)

Max Activating Token Index: 741

Text #13

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0081. Min Act: -0.1700

Data Index: 4969865 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0050. Min Act: -0.1700

Data Index: 4079488 (Open Web Text)

Max Activating Token Index: 555

Text #15

Max Range: 3.2116. Min Range: -3.2116

Max Act: 3.0050. Min Act: -0.1700

Data Index: 1603053 (Open Web Text)

Max Activating Token Index: 536

Text #16

Max Range: 3.2116. Min Range: -3.2116

Max Act: 2.9805. Min Act: -0.1700

Data Index: 7419453 (Open Web Text)

Max Activating Token Index: 523

Text #17

Max Range: 3.2116. Min Range: -3.2116

Max Act: 2.9932. Min Act: -0.1700

Data Index: 5653207 (Open Web Text)

Max Activating Token Index: 46

Text #18

Max Range: 3.2116. Min Range: -3.2116

Max Act: 2.9911. Min Act: -0.1700

Data Index: 5970730 (Open Web Text)

Max Activating Token Index: 301

Text #19

Max Range: 3.2116. Min Range: -3.2116

Max Act: 2.9912. Min Act: -0.1700

Data Index: 770259 (Open Web Text)

Max Activating Token Index: 32