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

Dataset: Open Web Text

Neuron 2022 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: 3.3003. Min Range: -3.3003

Max Act: 3.3003. Min Act: -0.1700

Data Index: 2844025 (Open Web Text)

Max Activating Token Index: 275

Text #1

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.0397. Min Act: -0.1700

Data Index: 6246003 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.0244. Min Act: -0.1700

Data Index: 4160018 (Open Web Text)

Max Activating Token Index: 69

Text #3

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.9962. Min Act: -0.1700

Data Index: 3098034 (Open Web Text)

Max Activating Token Index: 855

Text #4

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.9852. Min Act: -0.1700

Data Index: 7321567 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.9923. Min Act: -0.1700

Data Index: 5966611 (Open Web Text)

Max Activating Token Index: 997

Text #6

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.9315. Min Act: -0.1700

Data Index: 127924 (Open Web Text)

Max Activating Token Index: 276

Text #7

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.9185. Min Act: -0.1700

Data Index: 3043250 (Open Web Text)

Max Activating Token Index: 454

Text #8

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.9147. Min Act: -0.1700

Data Index: 7279699 (Open Web Text)

Max Activating Token Index: 662

Text #9

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.9529. Min Act: -0.1700

Data Index: 1816997 (Open Web Text)

Max Activating Token Index: 736

Text #10

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.9198. Min Act: -0.1700

Data Index: 6639707 (Open Web Text)

Max Activating Token Index: 985

Text #11

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.8754. Min Act: -0.1700

Data Index: 2541838 (Open Web Text)

Max Activating Token Index: 960

Text #12

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.9094. Min Act: -0.1700

Data Index: 7148849 (Open Web Text)

Max Activating Token Index: 582

Text #13

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.8959. Min Act: -0.1700

Data Index: 6783587 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.8844. Min Act: -0.1700

Data Index: 4698296 (Open Web Text)

Max Activating Token Index: 1016

Text #15

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.8484. Min Act: -0.1700

Data Index: 5010597 (Open Web Text)

Max Activating Token Index: 161

Text #16

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.8462. Min Act: -0.1700

Data Index: 5957537 (Open Web Text)

Max Activating Token Index: 398

Text #17

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.8358. Min Act: -0.1700

Data Index: 957893 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.8661. Min Act: -0.1700

Data Index: 651173 (Open Web Text)

Max Activating Token Index: 435

Text #19

Max Range: 3.3003. Min Range: -3.3003

Max Act: 2.8457. Min Act: -0.1700

Data Index: 590763 (Open Web Text)

Max Activating Token Index: 776