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

Dataset: Open Web Text

Neuron 1149 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: 5.6131. Min Range: -5.6131

Max Act: 5.6131. Min Act: -0.1700

Data Index: 1422873 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.5562. Min Act: -0.1696

Data Index: 3657406 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.4436. Min Act: -0.1608

Data Index: 7057598 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.3937. Min Act: -0.1700

Data Index: 3358901 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.4297. Min Act: -0.1691

Data Index: 432154 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.3994. Min Act: -0.1700

Data Index: 3379344 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.4278. Min Act: -0.1698

Data Index: 1452301 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.4071. Min Act: -0.1700

Data Index: 4240552 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.3612. Min Act: -0.1680

Data Index: 7410944 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.3434. Min Act: -0.1698

Data Index: 2420905 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.3493. Min Act: -0.1700

Data Index: 597030 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.3136. Min Act: -0.1700

Data Index: 2210221 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.3096. Min Act: -0.1700

Data Index: 5198005 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.3389. Min Act: -0.1700

Data Index: 7361097 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.3055. Min Act: -0.1699

Data Index: 4286560 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.3032. Min Act: -0.1696

Data Index: 4729436 (Open Web Text)

Max Activating Token Index: 404

Text #16

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.2733. Min Act: -0.1697

Data Index: 2081869 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.2772. Min Act: -0.1700

Data Index: 519523 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.2330. Min Act: -0.1700

Data Index: 3348496 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 5.6131. Min Range: -5.6131

Max Act: 5.2544. Min Act: -0.1700

Data Index: 2262260 (Open Web Text)

Max Activating Token Index: 9