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

Dataset: Open Web Text

Neuron 2394 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: 3.0389. Min Range: -3.0389

Max Act: 3.0389. Min Act: -0.1700

Data Index: 7424768 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.9588. Min Act: -0.1700

Data Index: 2283143 (Open Web Text)

Max Activating Token Index: 435

Text #2

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8966. Min Act: -0.1700

Data Index: 3138491 (Open Web Text)

Max Activating Token Index: 29

Text #3

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.9012. Min Act: -0.1700

Data Index: 2524502 (Open Web Text)

Max Activating Token Index: 420

Text #4

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8558. Min Act: -0.1700

Data Index: 632273 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8424. Min Act: -0.1700

Data Index: 3610419 (Open Web Text)

Max Activating Token Index: 380

Text #6

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8445. Min Act: -0.1700

Data Index: 5762471 (Open Web Text)

Max Activating Token Index: 613

Text #7

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8105. Min Act: -0.1700

Data Index: 626648 (Open Web Text)

Max Activating Token Index: 484

Text #8

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8102. Min Act: -0.1700

Data Index: 7101269 (Open Web Text)

Max Activating Token Index: 217

Text #9

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7815. Min Act: -0.1700

Data Index: 8095614 (Open Web Text)

Max Activating Token Index: 525

Text #10

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7930. Min Act: -0.1700

Data Index: 1458104 (Open Web Text)

Max Activating Token Index: 223

Text #11

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7982. Min Act: -0.1700

Data Index: 2012393 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7822. Min Act: -0.1700

Data Index: 713074 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7739. Min Act: -0.1700

Data Index: 3633050 (Open Web Text)

Max Activating Token Index: 798

Text #14

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7482. Min Act: -0.1700

Data Index: 2247774 (Open Web Text)

Max Activating Token Index: 793

Text #15

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7647. Min Act: -0.1700

Data Index: 1720642 (Open Web Text)

Max Activating Token Index: 55

Text #16

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7670. Min Act: -0.1700

Data Index: 5073086 (Open Web Text)

Max Activating Token Index: 385

Text #17

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7601. Min Act: -0.1700

Data Index: 970245 (Open Web Text)

Max Activating Token Index: 571

Text #18

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7624. Min Act: -0.1700

Data Index: 6713115 (Open Web Text)

Max Activating Token Index: 84

Text #19

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7528. Min Act: -0.1700

Data Index: 6207196 (Open Web Text)

Max Activating Token Index: 309