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

Dataset: Open Web Text

Neuron 532 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: 5.0472. Min Range: -5.0472

Max Act: 5.0472. Min Act: -0.1700

Data Index: 7642001 (Open Web Text)

Max Activating Token Index: 149

Text #1

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.9938. Min Act: -0.1700

Data Index: 5431575 (Open Web Text)

Max Activating Token Index: 448

Text #2

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.9298. Min Act: -0.1700

Data Index: 4402542 (Open Web Text)

Max Activating Token Index: 184

Text #3

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8991. Min Act: -0.1700

Data Index: 5697799 (Open Web Text)

Max Activating Token Index: 240

Text #4

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8816. Min Act: -0.1700

Data Index: 4945272 (Open Web Text)

Max Activating Token Index: 157

Text #5

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8432. Min Act: -0.1700

Data Index: 4848553 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8364. Min Act: -0.1700

Data Index: 7948962 (Open Web Text)

Max Activating Token Index: 930

Text #7

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8336. Min Act: -0.1700

Data Index: 5644090 (Open Web Text)

Max Activating Token Index: 549

Text #8

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8211. Min Act: -0.1700

Data Index: 3774550 (Open Web Text)

Max Activating Token Index: 178

Text #9

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8046. Min Act: -0.1700

Data Index: 8825136 (Open Web Text)

Max Activating Token Index: 922

Text #10

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8472. Min Act: -0.1700

Data Index: 4761236 (Open Web Text)

Max Activating Token Index: 496

Text #11

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.7934. Min Act: -0.1700

Data Index: 77583 (Open Web Text)

Max Activating Token Index: 995

Text #12

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8123. Min Act: -0.1700

Data Index: 7176117 (Open Web Text)

Max Activating Token Index: 856

Text #13

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8150. Min Act: -0.1700

Data Index: 6842156 (Open Web Text)

Max Activating Token Index: 338

Text #14

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8081. Min Act: -0.1700

Data Index: 1416288 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8231. Min Act: -0.1700

Data Index: 3555395 (Open Web Text)

Max Activating Token Index: 610

Text #16

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.7931. Min Act: -0.1700

Data Index: 3464847 (Open Web Text)

Max Activating Token Index: 849

Text #17

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8156. Min Act: -0.1700

Data Index: 3213358 (Open Web Text)

Max Activating Token Index: 209

Text #18

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.7902. Min Act: -0.1700

Data Index: 247504 (Open Web Text)

Max Activating Token Index: 112

Text #19

Max Range: 5.0472. Min Range: -5.0472

Max Act: 4.8013. Min Act: -0.1700

Data Index: 1273363 (Open Web Text)

Max Activating Token Index: 942