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

Dataset: Open Web Text

Neuron 938 in Layer 5

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: 4.8266. Min Range: -4.8266

Max Act: 4.8266. Min Act: -0.1700

Data Index: 19990 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.7647. Min Act: -0.1700

Data Index: 1309219 (Open Web Text)

Max Activating Token Index: 270

Text #2

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.7394. Min Act: -0.1700

Data Index: 8737256 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6619. Min Act: -0.1700

Data Index: 4872273 (Open Web Text)

Max Activating Token Index: 934

Text #4

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.7142. Min Act: -0.1700

Data Index: 1706271 (Open Web Text)

Max Activating Token Index: 950

Text #5

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6858. Min Act: -0.1700

Data Index: 5241001 (Open Web Text)

Max Activating Token Index: 627

Text #6

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6779. Min Act: -0.1700

Data Index: 5115642 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6150. Min Act: -0.1700

Data Index: 7150739 (Open Web Text)

Max Activating Token Index: 534

Text #8

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6363. Min Act: -0.1700

Data Index: 6514259 (Open Web Text)

Max Activating Token Index: 416

Text #9

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6781. Min Act: -0.1700

Data Index: 8414437 (Open Web Text)

Max Activating Token Index: 328

Text #10

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6498. Min Act: -0.1700

Data Index: 7589874 (Open Web Text)

Max Activating Token Index: 164

Text #11

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6238. Min Act: -0.1700

Data Index: 7488877 (Open Web Text)

Max Activating Token Index: 417

Text #12

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6261. Min Act: -0.1700

Data Index: 1601157 (Open Web Text)

Max Activating Token Index: 757

Text #13

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6272. Min Act: -0.1700

Data Index: 7439840 (Open Web Text)

Max Activating Token Index: 474

Text #14

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6514. Min Act: -0.1700

Data Index: 4444097 (Open Web Text)

Max Activating Token Index: 926

Text #15

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6103. Min Act: -0.1700

Data Index: 7802429 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.5956. Min Act: -0.1700

Data Index: 312153 (Open Web Text)

Max Activating Token Index: 800

Text #17

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.5863. Min Act: -0.1700

Data Index: 3053635 (Open Web Text)

Max Activating Token Index: 640

Text #18

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.6491. Min Act: -0.1700

Data Index: 3179963 (Open Web Text)

Max Activating Token Index: 547

Text #19

Max Range: 4.8266. Min Range: -4.8266

Max Act: 4.5911. Min Act: -0.1700

Data Index: 1227531 (Open Web Text)

Max Activating Token Index: 472