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

Dataset: Open Web Text

Neuron 1290 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: 3.9895. Min Range: -3.9895

Max Act: 3.9895. Min Act: -0.1700

Data Index: 8528218 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.9659. Min Act: -0.1700

Data Index: 2852091 (Open Web Text)

Max Activating Token Index: 805

Text #2

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.9426. Min Act: -0.1700

Data Index: 3901652 (Open Web Text)

Max Activating Token Index: 401

Text #3

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.9127. Min Act: -0.1700

Data Index: 1921051 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8886. Min Act: -0.1700

Data Index: 4739175 (Open Web Text)

Max Activating Token Index: 578

Text #5

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8730. Min Act: -0.1700

Data Index: 4478303 (Open Web Text)

Max Activating Token Index: 382

Text #6

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8327. Min Act: -0.1700

Data Index: 268425 (Open Web Text)

Max Activating Token Index: 764

Text #7

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8529. Min Act: -0.1700

Data Index: 3644950 (Open Web Text)

Max Activating Token Index: 132

Text #8

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8354. Min Act: -0.1700

Data Index: 5318889 (Open Web Text)

Max Activating Token Index: 403

Text #9

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8323. Min Act: -0.1700

Data Index: 3022575 (Open Web Text)

Max Activating Token Index: 90

Text #10

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8309. Min Act: -0.1700

Data Index: 6532061 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8050. Min Act: -0.1700

Data Index: 2110113 (Open Web Text)

Max Activating Token Index: 1004

Text #12

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8187. Min Act: -0.1700

Data Index: 1206850 (Open Web Text)

Max Activating Token Index: 75

Text #13

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.7938. Min Act: -0.1700

Data Index: 1496307 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8165. Min Act: -0.1700

Data Index: 2527279 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8140. Min Act: -0.1700

Data Index: 3093454 (Open Web Text)

Max Activating Token Index: 742

Text #16

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8292. Min Act: -0.1700

Data Index: 4978662 (Open Web Text)

Max Activating Token Index: 607

Text #17

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.7560. Min Act: -0.1700

Data Index: 876680 (Open Web Text)

Max Activating Token Index: 183

Text #18

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.7703. Min Act: -0.1700

Data Index: 2633587 (Open Web Text)

Max Activating Token Index: 589

Text #19

Max Range: 3.9895. Min Range: -3.9895

Max Act: 3.8140. Min Act: -0.1700

Data Index: 833510 (Open Web Text)

Max Activating Token Index: 803