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

Dataset: Open Web Text

Neuron 488 in Layer 0

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: 3.4065. Min Range: -3.4065

Max Act: 3.4065. Min Act: -0.1700

Data Index: 4942632 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.4007. Min Act: -0.1700

Data Index: 6689127 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.3907. Min Act: -0.1700

Data Index: 1527714 (Open Web Text)

Max Activating Token Index: 49

Text #3

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.3698. Min Act: -0.1700

Data Index: 4331979 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.3530. Min Act: -0.1700

Data Index: 2529083 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.3580. Min Act: -0.1700

Data Index: 4427778 (Open Web Text)

Max Activating Token Index: 749

Text #6

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.3223. Min Act: -0.1700

Data Index: 4762201 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.3012. Min Act: -0.1700

Data Index: 7852600 (Open Web Text)

Max Activating Token Index: 282

Text #8

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2958. Min Act: -0.1700

Data Index: 4138548 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.3043. Min Act: -0.1700

Data Index: 5031444 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2874. Min Act: -0.1700

Data Index: 7097480 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2840. Min Act: -0.1700

Data Index: 8327425 (Open Web Text)

Max Activating Token Index: 574

Text #12

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2612. Min Act: -0.1700

Data Index: 5211268 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2677. Min Act: -0.1700

Data Index: 65670 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2546. Min Act: -0.1700

Data Index: 3343374 (Open Web Text)

Max Activating Token Index: 666

Text #15

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2463. Min Act: -0.1700

Data Index: 4903914 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2507. Min Act: -0.1700

Data Index: 518833 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2437. Min Act: -0.1700

Data Index: 7097483 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2471. Min Act: -0.1700

Data Index: 4424031 (Open Web Text)

Max Activating Token Index: 207

Text #19

Max Range: 3.4065. Min Range: -3.4065

Max Act: 3.2429. Min Act: -0.1700

Data Index: 4990052 (Open Web Text)

Max Activating Token Index: 974