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

Dataset: Open Web Text

Neuron 283 in Layer 2

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: 3.8458. Min Range: -3.8458

Max Act: 3.8458. Min Act: -0.1700

Data Index: 4428842 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8414. Min Act: -0.1700

Data Index: 6587895 (Open Web Text)

Max Activating Token Index: 144

Text #2

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8176. Min Act: -0.1700

Data Index: 4055331 (Open Web Text)

Max Activating Token Index: 109

Text #3

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8157. Min Act: -0.1700

Data Index: 5477798 (Open Web Text)

Max Activating Token Index: 157

Text #4

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8434. Min Act: -0.1700

Data Index: 3772274 (Open Web Text)

Max Activating Token Index: 426

Text #5

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7992. Min Act: -0.1700

Data Index: 3406961 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8081. Min Act: -0.1700

Data Index: 661454 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7796. Min Act: -0.1700

Data Index: 2322708 (Open Web Text)

Max Activating Token Index: 561

Text #8

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8090. Min Act: -0.1700

Data Index: 6966052 (Open Web Text)

Max Activating Token Index: 370

Text #9

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7920. Min Act: -0.1700

Data Index: 4132955 (Open Web Text)

Max Activating Token Index: 959

Text #10

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8010. Min Act: -0.1700

Data Index: 1533785 (Open Web Text)

Max Activating Token Index: 133

Text #11

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7732. Min Act: -0.1700

Data Index: 6143942 (Open Web Text)

Max Activating Token Index: 55

Text #12

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7879. Min Act: -0.1700

Data Index: 5268972 (Open Web Text)

Max Activating Token Index: 787

Text #13

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7712. Min Act: -0.1700

Data Index: 2907021 (Open Web Text)

Max Activating Token Index: 557

Text #14

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8012. Min Act: -0.1700

Data Index: 2596036 (Open Web Text)

Max Activating Token Index: 354

Text #15

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7944. Min Act: -0.1700

Data Index: 4803213 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7970. Min Act: -0.1700

Data Index: 1979642 (Open Web Text)

Max Activating Token Index: 195

Text #17

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8003. Min Act: -0.1700

Data Index: 2583397 (Open Web Text)

Max Activating Token Index: 622

Text #18

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7870. Min Act: -0.1700

Data Index: 4772086 (Open Web Text)

Max Activating Token Index: 464

Text #19

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7903. Min Act: -0.1700

Data Index: 4505982 (Open Web Text)

Max Activating Token Index: 68