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

Dataset: Open Web Text

Neuron 1488 in Layer 3

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: 4.1344. Min Range: -4.1344

Max Act: 4.1344. Min Act: -0.1700

Data Index: 165261 (Open Web Text)

Max Activating Token Index: 855

Text #1

Max Range: 4.1344. Min Range: -4.1344

Max Act: 4.0858. Min Act: -0.1700

Data Index: 5332546 (Open Web Text)

Max Activating Token Index: 191

Text #2

Max Range: 4.1344. Min Range: -4.1344

Max Act: 4.0912. Min Act: -0.1700

Data Index: 6581916 (Open Web Text)

Max Activating Token Index: 995

Text #3

Max Range: 4.1344. Min Range: -4.1344

Max Act: 4.0293. Min Act: -0.1700

Data Index: 4713708 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.1344. Min Range: -4.1344

Max Act: 4.0063. Min Act: -0.1700

Data Index: 7945002 (Open Web Text)

Max Activating Token Index: 880

Text #5

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.9545. Min Act: -0.1700

Data Index: 6358040 (Open Web Text)

Max Activating Token Index: 300

Text #6

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.9529. Min Act: -0.1700

Data Index: 6215984 (Open Web Text)

Max Activating Token Index: 725

Text #7

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.9483. Min Act: -0.1700

Data Index: 4780745 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.9072. Min Act: -0.1700

Data Index: 5332547 (Open Web Text)

Max Activating Token Index: 594

Text #9

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.8700. Min Act: -0.1700

Data Index: 1568412 (Open Web Text)

Max Activating Token Index: 879

Text #10

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.8903. Min Act: -0.1700

Data Index: 3509684 (Open Web Text)

Max Activating Token Index: 838

Text #11

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.8530. Min Act: -0.1700

Data Index: 72123 (Open Web Text)

Max Activating Token Index: 914

Text #12

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.8786. Min Act: -0.1700

Data Index: 4899451 (Open Web Text)

Max Activating Token Index: 924

Text #13

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.8067. Min Act: -0.1700

Data Index: 230562 (Open Web Text)

Max Activating Token Index: 981

Text #14

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.8031. Min Act: -0.1700

Data Index: 1228533 (Open Web Text)

Max Activating Token Index: 389

Text #15

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.8419. Min Act: -0.1700

Data Index: 157672 (Open Web Text)

Max Activating Token Index: 852

Text #16

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.8303. Min Act: -0.1700

Data Index: 8449130 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.8538. Min Act: -0.1700

Data Index: 417605 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.7979. Min Act: -0.1700

Data Index: 6016565 (Open Web Text)

Max Activating Token Index: 762

Text #19

Max Range: 4.1344. Min Range: -4.1344

Max Act: 3.8146. Min Act: -0.1700

Data Index: 5709232 (Open Web Text)

Max Activating Token Index: 190