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

Dataset: Open Web Text

Neuron 2649 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: 3.2218. Min Range: -3.2218

Max Act: 3.2218. Min Act: -0.1700

Data Index: 38944 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.1679. Min Act: -0.1700

Data Index: 5172548 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.1550. Min Act: -0.1700

Data Index: 7615003 (Open Web Text)

Max Activating Token Index: 505

Text #3

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.1240. Min Act: -0.1700

Data Index: 5299123 (Open Web Text)

Max Activating Token Index: 946

Text #4

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.1143. Min Act: -0.1700

Data Index: 8490409 (Open Web Text)

Max Activating Token Index: 202

Text #5

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.1086. Min Act: -0.1700

Data Index: 3224555 (Open Web Text)

Max Activating Token Index: 313

Text #6

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0901. Min Act: -0.1700

Data Index: 5047326 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0740. Min Act: -0.1700

Data Index: 7742021 (Open Web Text)

Max Activating Token Index: 766

Text #8

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0711. Min Act: -0.1700

Data Index: 8615381 (Open Web Text)

Max Activating Token Index: 1006

Text #9

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0822. Min Act: -0.1700

Data Index: 1205505 (Open Web Text)

Max Activating Token Index: 382

Text #10

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0953. Min Act: -0.1700

Data Index: 1370019 (Open Web Text)

Max Activating Token Index: 466

Text #11

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0772. Min Act: -0.1700

Data Index: 2827606 (Open Web Text)

Max Activating Token Index: 88

Text #12

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0832. Min Act: -0.1700

Data Index: 8121464 (Open Web Text)

Max Activating Token Index: 669

Text #13

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0595. Min Act: -0.1700

Data Index: 3986632 (Open Web Text)

Max Activating Token Index: 923

Text #14

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0537. Min Act: -0.1700

Data Index: 6411660 (Open Web Text)

Max Activating Token Index: 204

Text #15

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0564. Min Act: -0.1700

Data Index: 121872 (Open Web Text)

Max Activating Token Index: 49

Text #16

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0349. Min Act: -0.1700

Data Index: 4066248 (Open Web Text)

Max Activating Token Index: 444

Text #17

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0529. Min Act: -0.1700

Data Index: 8278129 (Open Web Text)

Max Activating Token Index: 548

Text #18

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0532. Min Act: -0.1700

Data Index: 7489718 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 3.2218. Min Range: -3.2218

Max Act: 3.0422. Min Act: -0.1700

Data Index: 4591573 (Open Web Text)

Max Activating Token Index: 881