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

Dataset: Open Web Text

Neuron 2807 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: 3.2932. Min Range: -3.2932

Max Act: 3.2932. Min Act: -0.1700

Data Index: 3680327 (Open Web Text)

Max Activating Token Index: 556

Text #1

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1554. Min Act: -0.1700

Data Index: 6591128 (Open Web Text)

Max Activating Token Index: 651

Text #2

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1549. Min Act: -0.1700

Data Index: 5962691 (Open Web Text)

Max Activating Token Index: 730

Text #3

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1376. Min Act: -0.1700

Data Index: 3712630 (Open Web Text)

Max Activating Token Index: 713

Text #4

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0950. Min Act: -0.1700

Data Index: 1037760 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1214. Min Act: -0.1700

Data Index: 4199093 (Open Web Text)

Max Activating Token Index: 787

Text #6

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1221. Min Act: -0.1700

Data Index: 7923547 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0814. Min Act: -0.1700

Data Index: 3186263 (Open Web Text)

Max Activating Token Index: 438

Text #8

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0746. Min Act: -0.1700

Data Index: 3189722 (Open Web Text)

Max Activating Token Index: 582

Text #9

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0803. Min Act: -0.1700

Data Index: 7025230 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0367. Min Act: -0.1700

Data Index: 6537560 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0512. Min Act: -0.1700

Data Index: 4372012 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0654. Min Act: -0.1700

Data Index: 5025135 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0232. Min Act: -0.1700

Data Index: 5908091 (Open Web Text)

Max Activating Token Index: 348

Text #14

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0124. Min Act: -0.1700

Data Index: 2305692 (Open Web Text)

Max Activating Token Index: 353

Text #15

Max Range: 3.2932. Min Range: -3.2932

Max Act: 2.9802. Min Act: -0.1700

Data Index: 7800126 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 3.2932. Min Range: -3.2932

Max Act: 2.9980. Min Act: -0.1700

Data Index: 7667531 (Open Web Text)

Max Activating Token Index: 711

Text #17

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0064. Min Act: -0.1700

Data Index: 3716096 (Open Web Text)

Max Activating Token Index: 86

Text #18

Max Range: 3.2932. Min Range: -3.2932

Max Act: 2.9937. Min Act: -0.1700

Data Index: 7969562 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.0087. Min Act: -0.1700

Data Index: 8745863 (Open Web Text)

Max Activating Token Index: 224