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

Dataset: Open Web Text

Neuron 850 in Layer 1

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: 5.4890. Min Range: -5.4890

Max Act: 5.4890. Min Act: -0.1700

Data Index: 3080782 (Open Web Text)

Max Activating Token Index: 45

Text #1

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4438. Min Act: -0.1700

Data Index: 4162182 (Open Web Text)

Max Activating Token Index: 759

Text #2

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4678. Min Act: -0.1700

Data Index: 8370528 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4420. Min Act: -0.1700

Data Index: 1245174 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4453. Min Act: -0.1700

Data Index: 7358318 (Open Web Text)

Max Activating Token Index: 269

Text #5

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4544. Min Act: -0.1700

Data Index: 1974262 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4536. Min Act: -0.1700

Data Index: 6066946 (Open Web Text)

Max Activating Token Index: 37

Text #7

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4495. Min Act: -0.1700

Data Index: 5786790 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4698. Min Act: -0.1700

Data Index: 8570430 (Open Web Text)

Max Activating Token Index: 24

Text #9

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4135. Min Act: -0.1700

Data Index: 1869247 (Open Web Text)

Max Activating Token Index: 353

Text #10

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4327. Min Act: -0.1700

Data Index: 6607381 (Open Web Text)

Max Activating Token Index: 361

Text #11

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4082. Min Act: -0.1700

Data Index: 7231643 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.3978. Min Act: -0.1700

Data Index: 7252680 (Open Web Text)

Max Activating Token Index: 466

Text #13

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4180. Min Act: -0.1700

Data Index: 7252956 (Open Web Text)

Max Activating Token Index: 611

Text #14

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4088. Min Act: -0.1700

Data Index: 1799960 (Open Web Text)

Max Activating Token Index: 670

Text #15

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4133. Min Act: -0.1700

Data Index: 5289244 (Open Web Text)

Max Activating Token Index: 771

Text #16

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4014. Min Act: -0.1700

Data Index: 2813442 (Open Web Text)

Max Activating Token Index: 407

Text #17

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4427. Min Act: -0.1700

Data Index: 7814134 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4319. Min Act: -0.1700

Data Index: 4786013 (Open Web Text)

Max Activating Token Index: 295

Text #19

Max Range: 5.4890. Min Range: -5.4890

Max Act: 5.4168. Min Act: -0.1700

Data Index: 8013428 (Open Web Text)

Max Activating Token Index: 51