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

Dataset: Open Web Text

Neuron 3065 in Layer 6

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: 3.3567. Min Range: -3.3567

Max Act: 3.3567. Min Act: -0.1700

Data Index: 6602569 (Open Web Text)

Max Activating Token Index: 542

Text #1

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.3118. Min Act: -0.1700

Data Index: 1997545 (Open Web Text)

Max Activating Token Index: 774

Text #2

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2840. Min Act: -0.1700

Data Index: 4116020 (Open Web Text)

Max Activating Token Index: 103

Text #3

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2820. Min Act: -0.1700

Data Index: 4766905 (Open Web Text)

Max Activating Token Index: 837

Text #4

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2822. Min Act: -0.1700

Data Index: 1997549 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2754. Min Act: -0.1700

Data Index: 5618321 (Open Web Text)

Max Activating Token Index: 796

Text #6

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2690. Min Act: -0.1700

Data Index: 5608213 (Open Web Text)

Max Activating Token Index: 661

Text #7

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2768. Min Act: -0.1700

Data Index: 8091533 (Open Web Text)

Max Activating Token Index: 837

Text #8

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2634. Min Act: -0.1700

Data Index: 697363 (Open Web Text)

Max Activating Token Index: 555

Text #9

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2360. Min Act: -0.1700

Data Index: 6381513 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2294. Min Act: -0.1700

Data Index: 5867828 (Open Web Text)

Max Activating Token Index: 394

Text #11

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2186. Min Act: -0.1700

Data Index: 4268057 (Open Web Text)

Max Activating Token Index: 922

Text #12

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2434. Min Act: -0.1700

Data Index: 8255501 (Open Web Text)

Max Activating Token Index: 929

Text #13

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2272. Min Act: -0.1700

Data Index: 2337354 (Open Web Text)

Max Activating Token Index: 736

Text #14

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2061. Min Act: -0.1700

Data Index: 5166526 (Open Web Text)

Max Activating Token Index: 439

Text #15

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2258. Min Act: -0.1700

Data Index: 7672147 (Open Web Text)

Max Activating Token Index: 658

Text #16

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2171. Min Act: -0.1700

Data Index: 1643244 (Open Web Text)

Max Activating Token Index: 530

Text #17

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2054. Min Act: -0.1700

Data Index: 7479008 (Open Web Text)

Max Activating Token Index: 158

Text #18

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2096. Min Act: -0.1700

Data Index: 3616740 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 3.3567. Min Range: -3.3567

Max Act: 3.2244. Min Act: -0.1700

Data Index: 4237574 (Open Web Text)

Max Activating Token Index: 293