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

Dataset: Open Web Text

Neuron 1168 in Layer 3

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: 4.7448. Min Range: -4.7448

Max Act: 4.7448. Min Act: -0.1700

Data Index: 7411609 (Open Web Text)

Max Activating Token Index: 57

Text #1

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.3912. Min Act: -0.1700

Data Index: 2987630 (Open Web Text)

Max Activating Token Index: 408

Text #2

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.3748. Min Act: -0.1700

Data Index: 8420721 (Open Web Text)

Max Activating Token Index: 126

Text #3

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2959. Min Act: -0.1700

Data Index: 6327832 (Open Web Text)

Max Activating Token Index: 83

Text #4

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.3128. Min Act: -0.1700

Data Index: 7411605 (Open Web Text)

Max Activating Token Index: 344

Text #5

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2982. Min Act: -0.1700

Data Index: 6605159 (Open Web Text)

Max Activating Token Index: 901

Text #6

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.3032. Min Act: -0.1700

Data Index: 6173503 (Open Web Text)

Max Activating Token Index: 729

Text #7

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2904. Min Act: -0.1700

Data Index: 3743119 (Open Web Text)

Max Activating Token Index: 105

Text #8

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.3025. Min Act: -0.1700

Data Index: 3442056 (Open Web Text)

Max Activating Token Index: 946

Text #9

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2828. Min Act: -0.1700

Data Index: 529699 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2781. Min Act: -0.1700

Data Index: 8797894 (Open Web Text)

Max Activating Token Index: 107

Text #11

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2588. Min Act: -0.1700

Data Index: 6278208 (Open Web Text)

Max Activating Token Index: 141

Text #12

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2743. Min Act: -0.1700

Data Index: 6094134 (Open Web Text)

Max Activating Token Index: 780

Text #13

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2821. Min Act: -0.1700

Data Index: 6756208 (Open Web Text)

Max Activating Token Index: 198

Text #14

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2650. Min Act: -0.1700

Data Index: 3152792 (Open Web Text)

Max Activating Token Index: 119

Text #15

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2290. Min Act: -0.1700

Data Index: 4868369 (Open Web Text)

Max Activating Token Index: 86

Text #16

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2506. Min Act: -0.1700

Data Index: 6669711 (Open Web Text)

Max Activating Token Index: 100

Text #17

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2294. Min Act: -0.1700

Data Index: 5331990 (Open Web Text)

Max Activating Token Index: 138

Text #18

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2471. Min Act: -0.1700

Data Index: 5541956 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 4.7448. Min Range: -4.7448

Max Act: 4.2399. Min Act: -0.1700

Data Index: 6778813 (Open Web Text)

Max Activating Token Index: 696