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

Dataset: Open Web Text

Neuron 984 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: 4.0418. Min Range: -4.0418

Max Act: 4.0418. Min Act: -0.1700

Data Index: 6803593 (Open Web Text)

Max Activating Token Index: 636

Text #1

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8589. Min Act: -0.1700

Data Index: 3116800 (Open Web Text)

Max Activating Token Index: 941

Text #2

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8885. Min Act: -0.1700

Data Index: 162749 (Open Web Text)

Max Activating Token Index: 651

Text #3

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8463. Min Act: -0.1700

Data Index: 514382 (Open Web Text)

Max Activating Token Index: 169

Text #4

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8289. Min Act: -0.1700

Data Index: 6896812 (Open Web Text)

Max Activating Token Index: 519

Text #5

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8294. Min Act: -0.1700

Data Index: 6316438 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7678. Min Act: -0.1700

Data Index: 7454977 (Open Web Text)

Max Activating Token Index: 814

Text #7

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8116. Min Act: -0.1700

Data Index: 2698291 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7819. Min Act: -0.1700

Data Index: 64814 (Open Web Text)

Max Activating Token Index: 557

Text #9

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8049. Min Act: -0.1700

Data Index: 779440 (Open Web Text)

Max Activating Token Index: 751

Text #10

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7819. Min Act: -0.1700

Data Index: 3267936 (Open Web Text)

Max Activating Token Index: 932

Text #11

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7610. Min Act: -0.1700

Data Index: 6009643 (Open Web Text)

Max Activating Token Index: 956

Text #12

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7514. Min Act: -0.1700

Data Index: 3653316 (Open Web Text)

Max Activating Token Index: 641

Text #13

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7838. Min Act: -0.1700

Data Index: 1108634 (Open Web Text)

Max Activating Token Index: 454

Text #14

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7837. Min Act: -0.1700

Data Index: 8307641 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7805. Min Act: -0.1700

Data Index: 5594057 (Open Web Text)

Max Activating Token Index: 245

Text #16

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7619. Min Act: -0.1700

Data Index: 6420263 (Open Web Text)

Max Activating Token Index: 784

Text #17

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7329. Min Act: -0.1700

Data Index: 3101893 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7586. Min Act: -0.1700

Data Index: 3454904 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.7404. Min Act: -0.1700

Data Index: 6209243 (Open Web Text)

Max Activating Token Index: 182