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

Dataset: Open Web Text

Neuron 635 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: 3.0413. Min Range: -3.0413

Max Act: 3.0413. Min Act: -0.1700

Data Index: 2879622 (Open Web Text)

Max Activating Token Index: 587

Text #1

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8846. Min Act: -0.1700

Data Index: 4960187 (Open Web Text)

Max Activating Token Index: 789

Text #2

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8713. Min Act: -0.1700

Data Index: 4138621 (Open Web Text)

Max Activating Token Index: 919

Text #3

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8886. Min Act: -0.1700

Data Index: 1329703 (Open Web Text)

Max Activating Token Index: 634

Text #4

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8436. Min Act: -0.1700

Data Index: 191162 (Open Web Text)

Max Activating Token Index: 304

Text #5

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8615. Min Act: -0.1700

Data Index: 6625442 (Open Web Text)

Max Activating Token Index: 416

Text #6

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8546. Min Act: -0.1700

Data Index: 5203686 (Open Web Text)

Max Activating Token Index: 918

Text #7

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8455. Min Act: -0.1700

Data Index: 5542676 (Open Web Text)

Max Activating Token Index: 44

Text #8

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8485. Min Act: -0.1700

Data Index: 2322480 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8204. Min Act: -0.1700

Data Index: 1085826 (Open Web Text)

Max Activating Token Index: 958

Text #10

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8236. Min Act: -0.1700

Data Index: 2101153 (Open Web Text)

Max Activating Token Index: 343

Text #11

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8266. Min Act: -0.1700

Data Index: 5860134 (Open Web Text)

Max Activating Token Index: 996

Text #12

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8159. Min Act: -0.1700

Data Index: 2315067 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.7997. Min Act: -0.1700

Data Index: 7228633 (Open Web Text)

Max Activating Token Index: 682

Text #14

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8039. Min Act: -0.1700

Data Index: 8747256 (Open Web Text)

Max Activating Token Index: 178

Text #15

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8093. Min Act: -0.1700

Data Index: 8712616 (Open Web Text)

Max Activating Token Index: 845

Text #16

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.8151. Min Act: -0.1700

Data Index: 241550 (Open Web Text)

Max Activating Token Index: 425

Text #17

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.7620. Min Act: -0.1700

Data Index: 1259105 (Open Web Text)

Max Activating Token Index: 513

Text #18

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.7821. Min Act: -0.1700

Data Index: 5605200 (Open Web Text)

Max Activating Token Index: 846

Text #19

Max Range: 3.0413. Min Range: -3.0413

Max Act: 2.7601. Min Act: -0.1700

Data Index: 3798254 (Open Web Text)

Max Activating Token Index: 669