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

Dataset: Open Web Text

Neuron 2510 in Layer 5

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: 5.1472. Min Range: -5.1472

Max Act: 5.1459. Min Act: -0.1700

Data Index: 8825175 (Open Web Text)

Max Activating Token Index: 733

Text #1

Max Range: 5.1472. Min Range: -5.1472

Max Act: 5.1472. Min Act: -0.1700

Data Index: 4590521 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 5.1472. Min Range: -5.1472

Max Act: 5.0399. Min Act: -0.1700

Data Index: 476418 (Open Web Text)

Max Activating Token Index: 528

Text #3

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.9872. Min Act: -0.1700

Data Index: 8018143 (Open Web Text)

Max Activating Token Index: 833

Text #4

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.9218. Min Act: -0.1700

Data Index: 3184175 (Open Web Text)

Max Activating Token Index: 134

Text #5

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.9336. Min Act: -0.1700

Data Index: 4897467 (Open Web Text)

Max Activating Token Index: 184

Text #6

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8926. Min Act: -0.1700

Data Index: 3637867 (Open Web Text)

Max Activating Token Index: 141

Text #7

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8976. Min Act: -0.1700

Data Index: 1082319 (Open Web Text)

Max Activating Token Index: 507

Text #8

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.9261. Min Act: -0.1700

Data Index: 1931853 (Open Web Text)

Max Activating Token Index: 942

Text #9

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8890. Min Act: -0.1700

Data Index: 5020100 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8487. Min Act: -0.1700

Data Index: 2028540 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8718. Min Act: -0.1700

Data Index: 7065470 (Open Web Text)

Max Activating Token Index: 927

Text #12

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8834. Min Act: -0.1700

Data Index: 3008862 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8801. Min Act: -0.1700

Data Index: 3041033 (Open Web Text)

Max Activating Token Index: 862

Text #14

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8788. Min Act: -0.1700

Data Index: 7839049 (Open Web Text)

Max Activating Token Index: 965

Text #15

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8556. Min Act: -0.1700

Data Index: 5622310 (Open Web Text)

Max Activating Token Index: 818

Text #16

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8591. Min Act: -0.1700

Data Index: 6446976 (Open Web Text)

Max Activating Token Index: 848

Text #17

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8039. Min Act: -0.1700

Data Index: 2330854 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8174. Min Act: -0.1700

Data Index: 7649082 (Open Web Text)

Max Activating Token Index: 747

Text #19

Max Range: 5.1472. Min Range: -5.1472

Max Act: 4.8308. Min Act: -0.1700

Data Index: 7812566 (Open Web Text)

Max Activating Token Index: 523