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

Dataset: Open Web Text

Neuron 2808 in Layer 1

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: 1.6278. Min Range: -1.6278

Max Act: 1.6278. Min Act: -0.1700

Data Index: 3806250 (Open Web Text)

Max Activating Token Index: 810

Text #1

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.6134. Min Act: -0.1700

Data Index: 1585461 (Open Web Text)

Max Activating Token Index: 51

Text #2

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.6142. Min Act: -0.1700

Data Index: 7580632 (Open Web Text)

Max Activating Token Index: 700

Text #3

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.6133. Min Act: -0.1700

Data Index: 2950415 (Open Web Text)

Max Activating Token Index: 785

Text #4

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5988. Min Act: -0.1700

Data Index: 1109980 (Open Web Text)

Max Activating Token Index: 440

Text #5

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.6001. Min Act: -0.1700

Data Index: 1583705 (Open Web Text)

Max Activating Token Index: 694

Text #6

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5802. Min Act: -0.1700

Data Index: 5494890 (Open Web Text)

Max Activating Token Index: 283

Text #7

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5817. Min Act: -0.1700

Data Index: 8307640 (Open Web Text)

Max Activating Token Index: 650

Text #8

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5684. Min Act: -0.1699

Data Index: 3195106 (Open Web Text)

Max Activating Token Index: 562

Text #9

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5666. Min Act: -0.1700

Data Index: 4111156 (Open Web Text)

Max Activating Token Index: 1018

Text #10

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5726. Min Act: -0.1700

Data Index: 6954551 (Open Web Text)

Max Activating Token Index: 69

Text #11

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5710. Min Act: -0.1700

Data Index: 1889522 (Open Web Text)

Max Activating Token Index: 1014

Text #12

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5621. Min Act: -0.1700

Data Index: 8025887 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5500. Min Act: -0.1700

Data Index: 3147057 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5602. Min Act: -0.1700

Data Index: 874357 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5499. Min Act: -0.1700

Data Index: 5646045 (Open Web Text)

Max Activating Token Index: 388

Text #16

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5646. Min Act: -0.1700

Data Index: 3584124 (Open Web Text)

Max Activating Token Index: 502

Text #17

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5484. Min Act: -0.1700

Data Index: 7485201 (Open Web Text)

Max Activating Token Index: 382

Text #18

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5546. Min Act: -0.1700

Data Index: 6669786 (Open Web Text)

Max Activating Token Index: 243

Text #19

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.5585. Min Act: -0.1700

Data Index: 6772832 (Open Web Text)

Max Activating Token Index: 14