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

Dataset: Open Web Text

Neuron 1718 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: 4.0486. Min Range: -4.0486

Max Act: 4.0486. Min Act: -0.1700

Data Index: 256334 (Open Web Text)

Max Activating Token Index: 348

Text #1

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.9616. Min Act: -0.1700

Data Index: 6562924 (Open Web Text)

Max Activating Token Index: 387

Text #2

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.9576. Min Act: -0.1700

Data Index: 4298834 (Open Web Text)

Max Activating Token Index: 332

Text #3

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.9362. Min Act: -0.1700

Data Index: 4298847 (Open Web Text)

Max Activating Token Index: 716

Text #4

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.9313. Min Act: -0.1700

Data Index: 6271485 (Open Web Text)

Max Activating Token Index: 100

Text #5

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.9493. Min Act: -0.1700

Data Index: 381667 (Open Web Text)

Max Activating Token Index: 427

Text #6

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.8895. Min Act: -0.1700

Data Index: 52747 (Open Web Text)

Max Activating Token Index: 969

Text #7

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.8833. Min Act: -0.1700

Data Index: 8028212 (Open Web Text)

Max Activating Token Index: 624

Text #8

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.8603. Min Act: -0.1700

Data Index: 4945314 (Open Web Text)

Max Activating Token Index: 883

Text #9

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.8191. Min Act: -0.1700

Data Index: 3686814 (Open Web Text)

Max Activating Token Index: 205

Text #10

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.8168. Min Act: -0.1700

Data Index: 316233 (Open Web Text)

Max Activating Token Index: 700

Text #11

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.8369. Min Act: -0.1700

Data Index: 6105275 (Open Web Text)

Max Activating Token Index: 973

Text #12

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.8118. Min Act: -0.1700

Data Index: 4192044 (Open Web Text)

Max Activating Token Index: 316

Text #13

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.8015. Min Act: -0.1700

Data Index: 8313099 (Open Web Text)

Max Activating Token Index: 310

Text #14

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.7975. Min Act: -0.1700

Data Index: 3482189 (Open Web Text)

Max Activating Token Index: 852

Text #15

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.8015. Min Act: -0.1700

Data Index: 4242182 (Open Web Text)

Max Activating Token Index: 229

Text #16

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.7919. Min Act: -0.1700

Data Index: 2131505 (Open Web Text)

Max Activating Token Index: 369

Text #17

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.7808. Min Act: -0.1700

Data Index: 6041750 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.7816. Min Act: -0.1700

Data Index: 7910717 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 4.0486. Min Range: -4.0486

Max Act: 3.8114. Min Act: -0.1700

Data Index: 1229451 (Open Web Text)

Max Activating Token Index: 125