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

Dataset: Open Web Text

Neuron 730 in Layer 2

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: 4.4641. Min Range: -4.4641

Max Act: 4.4641. Min Act: -0.1700

Data Index: 362245 (Open Web Text)

Max Activating Token Index: 1004

Text #1

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.3701. Min Act: -0.1700

Data Index: 1495718 (Open Web Text)

Max Activating Token Index: 311

Text #2

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.3824. Min Act: -0.1700

Data Index: 4455552 (Open Web Text)

Max Activating Token Index: 946

Text #3

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.3754. Min Act: -0.1700

Data Index: 6721931 (Open Web Text)

Max Activating Token Index: 188

Text #4

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.3283. Min Act: -0.1700

Data Index: 2578152 (Open Web Text)

Max Activating Token Index: 89

Text #5

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2922. Min Act: -0.1700

Data Index: 4908447 (Open Web Text)

Max Activating Token Index: 165

Text #6

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2986. Min Act: -0.1700

Data Index: 2802344 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2756. Min Act: -0.1700

Data Index: 6941521 (Open Web Text)

Max Activating Token Index: 213

Text #8

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.3146. Min Act: -0.1700

Data Index: 6721933 (Open Web Text)

Max Activating Token Index: 660

Text #9

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2802. Min Act: -0.1700

Data Index: 21714 (Open Web Text)

Max Activating Token Index: 388

Text #10

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2646. Min Act: -0.1700

Data Index: 6636479 (Open Web Text)

Max Activating Token Index: 162

Text #11

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2770. Min Act: -0.1700

Data Index: 4772928 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2768. Min Act: -0.1700

Data Index: 7109909 (Open Web Text)

Max Activating Token Index: 139

Text #13

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2570. Min Act: -0.1700

Data Index: 2666191 (Open Web Text)

Max Activating Token Index: 701

Text #14

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2429. Min Act: -0.1700

Data Index: 572929 (Open Web Text)

Max Activating Token Index: 760

Text #15

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2495. Min Act: -0.1700

Data Index: 6390851 (Open Web Text)

Max Activating Token Index: 307

Text #16

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2395. Min Act: -0.1700

Data Index: 6034700 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2357. Min Act: -0.1700

Data Index: 6009844 (Open Web Text)

Max Activating Token Index: 886

Text #18

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2483. Min Act: -0.1700

Data Index: 4375308 (Open Web Text)

Max Activating Token Index: 641

Text #19

Max Range: 4.4641. Min Range: -4.4641

Max Act: 4.2336. Min Act: -0.1700

Data Index: 3698434 (Open Web Text)

Max Activating Token Index: 604