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

Dataset: Open Web Text

Neuron 2243 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: 3.3766. Min Range: -3.3766

Max Act: 3.3562. Min Act: -0.1700

Data Index: 7060017 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.3766. Min Act: -0.1700

Data Index: 6467035 (Open Web Text)

Max Activating Token Index: 477

Text #2

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.3127. Min Act: -0.1700

Data Index: 6744223 (Open Web Text)

Max Activating Token Index: 641

Text #3

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2496. Min Act: -0.1700

Data Index: 1812811 (Open Web Text)

Max Activating Token Index: 443

Text #4

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2664. Min Act: -0.1700

Data Index: 3971870 (Open Web Text)

Max Activating Token Index: 980

Text #5

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2546. Min Act: -0.1700

Data Index: 682269 (Open Web Text)

Max Activating Token Index: 565

Text #6

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2452. Min Act: -0.1700

Data Index: 863628 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2752. Min Act: -0.1700

Data Index: 2219171 (Open Web Text)

Max Activating Token Index: 710

Text #8

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2752. Min Act: -0.1700

Data Index: 7035789 (Open Web Text)

Max Activating Token Index: 564

Text #9

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2550. Min Act: -0.1700

Data Index: 8751968 (Open Web Text)

Max Activating Token Index: 431

Text #10

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2432. Min Act: -0.1700

Data Index: 4320583 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2424. Min Act: -0.1700

Data Index: 4883482 (Open Web Text)

Max Activating Token Index: 787

Text #12

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2593. Min Act: -0.1700

Data Index: 7803000 (Open Web Text)

Max Activating Token Index: 660

Text #13

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2303. Min Act: -0.1700

Data Index: 3452370 (Open Web Text)

Max Activating Token Index: 683

Text #14

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2447. Min Act: -0.1700

Data Index: 4242798 (Open Web Text)

Max Activating Token Index: 634

Text #15

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2533. Min Act: -0.1700

Data Index: 294934 (Open Web Text)

Max Activating Token Index: 359

Text #16

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2314. Min Act: -0.1700

Data Index: 5299193 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2626. Min Act: -0.1700

Data Index: 8159283 (Open Web Text)

Max Activating Token Index: 1017

Text #18

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2520. Min Act: -0.1700

Data Index: 5109247 (Open Web Text)

Max Activating Token Index: 610

Text #19

Max Range: 3.3766. Min Range: -3.3766

Max Act: 3.2194. Min Act: -0.1700

Data Index: 3633708 (Open Web Text)

Max Activating Token Index: 1006