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

Dataset: Open Web Text

Neuron 2086 in Layer 4

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: 4.3446. Min Range: -4.3446

Max Act: 4.3446. Min Act: -0.1700

Data Index: 3264017 (Open Web Text)

Max Activating Token Index: 47

Text #1

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.1959. Min Act: -0.1700

Data Index: 8796672 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.1493. Min Act: -0.1700

Data Index: 3131668 (Open Web Text)

Max Activating Token Index: 244

Text #3

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.1276. Min Act: -0.1700

Data Index: 4520649 (Open Web Text)

Max Activating Token Index: 330

Text #4

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.1172. Min Act: -0.1700

Data Index: 4987865 (Open Web Text)

Max Activating Token Index: 222

Text #5

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.0927. Min Act: -0.1700

Data Index: 8137021 (Open Web Text)

Max Activating Token Index: 487

Text #6

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.0795. Min Act: -0.1700

Data Index: 2012554 (Open Web Text)

Max Activating Token Index: 180

Text #7

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.0582. Min Act: -0.1700

Data Index: 8796671 (Open Web Text)

Max Activating Token Index: 703

Text #8

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.0588. Min Act: -0.1700

Data Index: 3338872 (Open Web Text)

Max Activating Token Index: 941

Text #9

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.0123. Min Act: -0.1700

Data Index: 6169714 (Open Web Text)

Max Activating Token Index: 1014

Text #10

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.0498. Min Act: -0.1700

Data Index: 1550252 (Open Web Text)

Max Activating Token Index: 312

Text #11

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.0158. Min Act: -0.1700

Data Index: 5469763 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 4.3446. Min Range: -4.3446

Max Act: 3.9870. Min Act: -0.1700

Data Index: 1460933 (Open Web Text)

Max Activating Token Index: 245

Text #13

Max Range: 4.3446. Min Range: -4.3446

Max Act: 4.0025. Min Act: -0.1700

Data Index: 7880598 (Open Web Text)

Max Activating Token Index: 316

Text #14

Max Range: 4.3446. Min Range: -4.3446

Max Act: 3.9687. Min Act: -0.1700

Data Index: 3662634 (Open Web Text)

Max Activating Token Index: 321

Text #15

Max Range: 4.3446. Min Range: -4.3446

Max Act: 3.9648. Min Act: -0.1700

Data Index: 8104197 (Open Web Text)

Max Activating Token Index: 483

Text #16

Max Range: 4.3446. Min Range: -4.3446

Max Act: 3.9798. Min Act: -0.1700

Data Index: 6803078 (Open Web Text)

Max Activating Token Index: 437

Text #17

Max Range: 4.3446. Min Range: -4.3446

Max Act: 3.9942. Min Act: -0.1700

Data Index: 7744277 (Open Web Text)

Max Activating Token Index: 792

Text #18

Max Range: 4.3446. Min Range: -4.3446

Max Act: 3.9472. Min Act: -0.1700

Data Index: 912716 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 4.3446. Min Range: -4.3446

Max Act: 3.9470. Min Act: -0.1700

Data Index: 7411119 (Open Web Text)

Max Activating Token Index: 465