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

Dataset: Open Web Text

Neuron 1827 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: 4.4964. Min Range: -4.4964

Max Act: 4.4964. Min Act: -0.1700

Data Index: 1809836 (Open Web Text)

Max Activating Token Index: 775

Text #1

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.4741. Min Act: -0.1700

Data Index: 5265328 (Open Web Text)

Max Activating Token Index: 953

Text #2

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.3957. Min Act: -0.1700

Data Index: 5701575 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.3754. Min Act: -0.1700

Data Index: 1709507 (Open Web Text)

Max Activating Token Index: 506

Text #4

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.3133. Min Act: -0.1700

Data Index: 6311517 (Open Web Text)

Max Activating Token Index: 167

Text #5

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.2601. Min Act: -0.1700

Data Index: 319331 (Open Web Text)

Max Activating Token Index: 727

Text #6

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.1928. Min Act: -0.1700

Data Index: 3974720 (Open Web Text)

Max Activating Token Index: 73

Text #7

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.1375. Min Act: -0.1700

Data Index: 1839727 (Open Web Text)

Max Activating Token Index: 162

Text #8

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.1482. Min Act: -0.1700

Data Index: 911337 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.1369. Min Act: -0.1700

Data Index: 3812226 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.1087. Min Act: -0.1700

Data Index: 6347489 (Open Web Text)

Max Activating Token Index: 226

Text #11

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.1116. Min Act: -0.1700

Data Index: 6694154 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.0887. Min Act: -0.1700

Data Index: 77111 (Open Web Text)

Max Activating Token Index: 162

Text #13

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.0496. Min Act: -0.1700

Data Index: 2449473 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 4.4964. Min Range: -4.4964

Max Act: 4.0601. Min Act: -0.1700

Data Index: 6311515 (Open Web Text)

Max Activating Token Index: 278

Text #15

Max Range: 4.4964. Min Range: -4.4964

Max Act: 3.9972. Min Act: -0.1700

Data Index: 1719234 (Open Web Text)

Max Activating Token Index: 867

Text #16

Max Range: 4.4964. Min Range: -4.4964

Max Act: 3.9812. Min Act: -0.1700

Data Index: 1925415 (Open Web Text)

Max Activating Token Index: 703

Text #17

Max Range: 4.4964. Min Range: -4.4964

Max Act: 3.9753. Min Act: -0.1700

Data Index: 2727714 (Open Web Text)

Max Activating Token Index: 225

Text #18

Max Range: 4.4964. Min Range: -4.4964

Max Act: 3.9614. Min Act: -0.1700

Data Index: 6261722 (Open Web Text)

Max Activating Token Index: 923

Text #19

Max Range: 4.4964. Min Range: -4.4964

Max Act: 3.9250. Min Act: -0.1700

Data Index: 5979250 (Open Web Text)

Max Activating Token Index: 484