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

Dataset: Open Web Text

Neuron 880 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: 3.1199. Min Range: -3.1199

Max Act: 3.1199. Min Act: -0.1700

Data Index: 1037995 (Open Web Text)

Max Activating Token Index: 571

Text #1

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0493. Min Act: -0.1700

Data Index: 4909734 (Open Web Text)

Max Activating Token Index: 309

Text #2

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0363. Min Act: -0.1700

Data Index: 6980658 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0191. Min Act: -0.1700

Data Index: 2610836 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0189. Min Act: -0.1700

Data Index: 1372497 (Open Web Text)

Max Activating Token Index: 245

Text #5

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0064. Min Act: -0.1700

Data Index: 384569 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9916. Min Act: -0.1700

Data Index: 482187 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9908. Min Act: -0.1700

Data Index: 5099994 (Open Web Text)

Max Activating Token Index: 342

Text #8

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0016. Min Act: -0.1700

Data Index: 2560174 (Open Web Text)

Max Activating Token Index: 608

Text #9

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9654. Min Act: -0.1700

Data Index: 6805637 (Open Web Text)

Max Activating Token Index: 670

Text #10

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9710. Min Act: -0.1700

Data Index: 7152739 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9492. Min Act: -0.1700

Data Index: 951275 (Open Web Text)

Max Activating Token Index: 458

Text #12

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9665. Min Act: -0.1700

Data Index: 7156189 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9504. Min Act: -0.1700

Data Index: 295109 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9673. Min Act: -0.1700

Data Index: 4246947 (Open Web Text)

Max Activating Token Index: 465

Text #15

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9464. Min Act: -0.1700

Data Index: 3171324 (Open Web Text)

Max Activating Token Index: 995

Text #16

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9406. Min Act: -0.1700

Data Index: 5762613 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9415. Min Act: -0.1700

Data Index: 370808 (Open Web Text)

Max Activating Token Index: 989

Text #18

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9535. Min Act: -0.1700

Data Index: 4458503 (Open Web Text)

Max Activating Token Index: 315

Text #19

Max Range: 3.1199. Min Range: -3.1199

Max Act: 2.9275. Min Act: -0.1700

Data Index: 4909732 (Open Web Text)

Max Activating Token Index: 995