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

Dataset: Open Web Text

Neuron 658 in Layer 2

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: 3.2001. Min Range: -3.2001

Max Act: 3.2001. Min Act: -0.1700

Data Index: 6411187 (Open Web Text)

Max Activating Token Index: 123

Text #1

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.1576. Min Act: -0.1700

Data Index: 4019157 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0902. Min Act: -0.1700

Data Index: 8603940 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0843. Min Act: -0.1700

Data Index: 3524089 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0811. Min Act: -0.1700

Data Index: 822375 (Open Web Text)

Max Activating Token Index: 693

Text #5

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0932. Min Act: -0.1700

Data Index: 5714652 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0680. Min Act: -0.1700

Data Index: 5093576 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0655. Min Act: -0.1700

Data Index: 3532155 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0598. Min Act: -0.1700

Data Index: 6897573 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0480. Min Act: -0.1700

Data Index: 1233048 (Open Web Text)

Max Activating Token Index: 71

Text #10

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0486. Min Act: -0.1700

Data Index: 3053856 (Open Web Text)

Max Activating Token Index: 400

Text #11

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0357. Min Act: -0.1700

Data Index: 8197136 (Open Web Text)

Max Activating Token Index: 136

Text #12

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0129. Min Act: -0.1700

Data Index: 3053851 (Open Web Text)

Max Activating Token Index: 526

Text #13

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0205. Min Act: -0.1700

Data Index: 3068157 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0198. Min Act: -0.1700

Data Index: 1945926 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.2001. Min Range: -3.2001

Max Act: 3.0112. Min Act: -0.1700

Data Index: 4036248 (Open Web Text)

Max Activating Token Index: 672

Text #16

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.9930. Min Act: -0.1700

Data Index: 8066461 (Open Web Text)

Max Activating Token Index: 954

Text #17

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.9983. Min Act: -0.1700

Data Index: 3053854 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.9917. Min Act: -0.1700

Data Index: 4631544 (Open Web Text)

Max Activating Token Index: 566

Text #19

Max Range: 3.2001. Min Range: -3.2001

Max Act: 2.9990. Min Act: -0.1700

Data Index: 7421013 (Open Web Text)

Max Activating Token Index: 549