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

Dataset: Open Web Text

Neuron 1982 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: 5.1672. Min Range: -5.1672

Max Act: 5.1071. Min Act: -0.1700

Data Index: 4144573 (Open Web Text)

Max Activating Token Index: 385

Text #1

Max Range: 5.1672. Min Range: -5.1672

Max Act: 5.1672. Min Act: -0.1700

Data Index: 8684509 (Open Web Text)

Max Activating Token Index: 777

Text #2

Max Range: 5.1672. Min Range: -5.1672

Max Act: 5.1161. Min Act: -0.1700

Data Index: 5157922 (Open Web Text)

Max Activating Token Index: 525

Text #3

Max Range: 5.1672. Min Range: -5.1672

Max Act: 5.1031. Min Act: -0.1700

Data Index: 3367173 (Open Web Text)

Max Activating Token Index: 631

Text #4

Max Range: 5.1672. Min Range: -5.1672

Max Act: 5.1050. Min Act: -0.1700

Data Index: 3326445 (Open Web Text)

Max Activating Token Index: 733

Text #5

Max Range: 5.1672. Min Range: -5.1672

Max Act: 5.0964. Min Act: -0.1700

Data Index: 5329637 (Open Web Text)

Max Activating Token Index: 783

Text #6

Max Range: 5.1672. Min Range: -5.1672

Max Act: 5.0716. Min Act: -0.1700

Data Index: 5900319 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 5.1672. Min Range: -5.1672

Max Act: 5.0632. Min Act: -0.1700

Data Index: 87369 (Open Web Text)

Max Activating Token Index: 304

Text #8

Max Range: 5.1672. Min Range: -5.1672

Max Act: 5.0434. Min Act: -0.1700

Data Index: 353389 (Open Web Text)

Max Activating Token Index: 995

Text #9

Max Range: 5.1672. Min Range: -5.1672

Max Act: 5.0082. Min Act: -0.1700

Data Index: 3519985 (Open Web Text)

Max Activating Token Index: 825

Text #10

Max Range: 5.1672. Min Range: -5.1672

Max Act: 5.0083. Min Act: -0.1700

Data Index: 6681677 (Open Web Text)

Max Activating Token Index: 589

Text #11

Max Range: 5.1672. Min Range: -5.1672

Max Act: 4.9550. Min Act: -0.1700

Data Index: 2502906 (Open Web Text)

Max Activating Token Index: 747

Text #12

Max Range: 5.1672. Min Range: -5.1672

Max Act: 4.8975. Min Act: -0.1700

Data Index: 1366391 (Open Web Text)

Max Activating Token Index: 150

Text #13

Max Range: 5.1672. Min Range: -5.1672

Max Act: 4.9109. Min Act: -0.1700

Data Index: 8266551 (Open Web Text)

Max Activating Token Index: 798

Text #14

Max Range: 5.1672. Min Range: -5.1672

Max Act: 4.8759. Min Act: -0.1700

Data Index: 5242377 (Open Web Text)

Max Activating Token Index: 453

Text #15

Max Range: 5.1672. Min Range: -5.1672

Max Act: 4.8980. Min Act: -0.1700

Data Index: 7072048 (Open Web Text)

Max Activating Token Index: 631

Text #16

Max Range: 5.1672. Min Range: -5.1672

Max Act: 4.8555. Min Act: -0.1700

Data Index: 638424 (Open Web Text)

Max Activating Token Index: 159

Text #17

Max Range: 5.1672. Min Range: -5.1672

Max Act: 4.8384. Min Act: -0.1700

Data Index: 1712701 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 5.1672. Min Range: -5.1672

Max Act: 4.8485. Min Act: -0.1700

Data Index: 2005833 (Open Web Text)

Max Activating Token Index: 118

Text #19

Max Range: 5.1672. Min Range: -5.1672

Max Act: 4.8396. Min Act: -0.1700

Data Index: 570627 (Open Web Text)

Max Activating Token Index: 43