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

Dataset: Open Web Text

Neuron 1525 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: 3.8786. Min Range: -3.8786

Max Act: 3.8786. Min Act: -0.1700

Data Index: 5616637 (Open Web Text)

Max Activating Token Index: 370

Text #1

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.8449. Min Act: -0.1700

Data Index: 8171072 (Open Web Text)

Max Activating Token Index: 643

Text #2

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.7712. Min Act: -0.1700

Data Index: 4506152 (Open Web Text)

Max Activating Token Index: 142

Text #3

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.7619. Min Act: -0.1700

Data Index: 8112369 (Open Web Text)

Max Activating Token Index: 555

Text #4

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.7455. Min Act: -0.1700

Data Index: 5576592 (Open Web Text)

Max Activating Token Index: 341

Text #5

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.7784. Min Act: -0.1700

Data Index: 6527338 (Open Web Text)

Max Activating Token Index: 565

Text #6

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.7348. Min Act: -0.1700

Data Index: 8350584 (Open Web Text)

Max Activating Token Index: 471

Text #7

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.7124. Min Act: -0.1700

Data Index: 7059781 (Open Web Text)

Max Activating Token Index: 999

Text #8

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.7174. Min Act: -0.1700

Data Index: 3363078 (Open Web Text)

Max Activating Token Index: 781

Text #9

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6782. Min Act: -0.1700

Data Index: 3263870 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6895. Min Act: -0.1700

Data Index: 6845203 (Open Web Text)

Max Activating Token Index: 123

Text #11

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.7120. Min Act: -0.1700

Data Index: 8754131 (Open Web Text)

Max Activating Token Index: 235

Text #12

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6899. Min Act: -0.1700

Data Index: 1603685 (Open Web Text)

Max Activating Token Index: 645

Text #13

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6696. Min Act: -0.1700

Data Index: 6518309 (Open Web Text)

Max Activating Token Index: 112

Text #14

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6709. Min Act: -0.1700

Data Index: 7132737 (Open Web Text)

Max Activating Token Index: 445

Text #15

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6737. Min Act: -0.1700

Data Index: 7564986 (Open Web Text)

Max Activating Token Index: 93

Text #16

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6636. Min Act: -0.1700

Data Index: 6600631 (Open Web Text)

Max Activating Token Index: 659

Text #17

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6624. Min Act: -0.1700

Data Index: 5040980 (Open Web Text)

Max Activating Token Index: 880

Text #18

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6448. Min Act: -0.1700

Data Index: 1926586 (Open Web Text)

Max Activating Token Index: 767

Text #19

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6661. Min Act: -0.1700

Data Index: 2454840 (Open Web Text)

Max Activating Token Index: 255