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

Dataset: Open Web Text

Neuron 809 in Layer 4

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: 3.6472. Min Range: -3.6472

Max Act: 3.6472. Min Act: -0.1700

Data Index: 6142259 (Open Web Text)

Max Activating Token Index: 469

Text #1

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.6406. Min Act: -0.1700

Data Index: 1847706 (Open Web Text)

Max Activating Token Index: 125

Text #2

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.6251. Min Act: -0.1700

Data Index: 988627 (Open Web Text)

Max Activating Token Index: 352

Text #3

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5997. Min Act: -0.1700

Data Index: 7300042 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5936. Min Act: -0.1700

Data Index: 1132643 (Open Web Text)

Max Activating Token Index: 249

Text #5

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.6176. Min Act: -0.1700

Data Index: 817319 (Open Web Text)

Max Activating Token Index: 87

Text #6

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.6319. Min Act: -0.1700

Data Index: 4680138 (Open Web Text)

Max Activating Token Index: 499

Text #7

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.6050. Min Act: -0.1700

Data Index: 5138994 (Open Web Text)

Max Activating Token Index: 87

Text #8

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5935. Min Act: -0.1700

Data Index: 8048900 (Open Web Text)

Max Activating Token Index: 25

Text #9

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.6323. Min Act: -0.1700

Data Index: 4515602 (Open Web Text)

Max Activating Token Index: 639

Text #10

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.6078. Min Act: -0.1700

Data Index: 419137 (Open Web Text)

Max Activating Token Index: 70

Text #11

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5830. Min Act: -0.1700

Data Index: 6654194 (Open Web Text)

Max Activating Token Index: 252

Text #12

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5322. Min Act: -0.1700

Data Index: 8748902 (Open Web Text)

Max Activating Token Index: 427

Text #13

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5810. Min Act: -0.1700

Data Index: 7927378 (Open Web Text)

Max Activating Token Index: 527

Text #14

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5865. Min Act: -0.1700

Data Index: 5483545 (Open Web Text)

Max Activating Token Index: 261

Text #15

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5705. Min Act: -0.1700

Data Index: 2638500 (Open Web Text)

Max Activating Token Index: 162

Text #16

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5670. Min Act: -0.1700

Data Index: 4737255 (Open Web Text)

Max Activating Token Index: 190

Text #17

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5760. Min Act: -0.1700

Data Index: 4858078 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5912. Min Act: -0.1700

Data Index: 4955869 (Open Web Text)

Max Activating Token Index: 446

Text #19

Max Range: 3.6472. Min Range: -3.6472

Max Act: 3.5485. Min Act: -0.1700

Data Index: 1537521 (Open Web Text)

Max Activating Token Index: 449