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

Dataset: Open Web Text

Neuron 1543 in Layer 0

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: 3.7876. Min Range: -3.7876

Max Act: 3.7721. Min Act: -0.1700

Data Index: 1004841 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7876. Min Act: -0.1700

Data Index: 7052436 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7397. Min Act: -0.1700

Data Index: 3376128 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7100. Min Act: -0.1700

Data Index: 2766278 (Open Web Text)

Max Activating Token Index: 315

Text #4

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6839. Min Act: -0.1700

Data Index: 3671843 (Open Web Text)

Max Activating Token Index: 56

Text #5

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6754. Min Act: -0.1700

Data Index: 255139 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6868. Min Act: -0.1700

Data Index: 6984229 (Open Web Text)

Max Activating Token Index: 353

Text #7

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6325. Min Act: -0.1700

Data Index: 3677678 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6192. Min Act: -0.1700

Data Index: 3864059 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6368. Min Act: -0.1700

Data Index: 4581554 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6264. Min Act: -0.1700

Data Index: 1518248 (Open Web Text)

Max Activating Token Index: 300

Text #11

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6094. Min Act: -0.1700

Data Index: 6961674 (Open Web Text)

Max Activating Token Index: 194

Text #12

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6135. Min Act: -0.1700

Data Index: 13238 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5883. Min Act: -0.1700

Data Index: 7338644 (Open Web Text)

Max Activating Token Index: 864

Text #14

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6123. Min Act: -0.1700

Data Index: 428585 (Open Web Text)

Max Activating Token Index: 404

Text #15

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5858. Min Act: -0.1700

Data Index: 6032620 (Open Web Text)

Max Activating Token Index: 228

Text #16

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5711. Min Act: -0.1700

Data Index: 8121801 (Open Web Text)

Max Activating Token Index: 440

Text #17

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5619. Min Act: -0.1700

Data Index: 6671690 (Open Web Text)

Max Activating Token Index: 447

Text #18

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5714. Min Act: -0.1700

Data Index: 1921789 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5727. Min Act: -0.1700

Data Index: 5893706 (Open Web Text)

Max Activating Token Index: 16