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

Dataset: Open Web Text

Neuron 53 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: 4.4006. Min Range: -4.4006

Max Act: 4.4006. Min Act: -0.1700

Data Index: 8755554 (Open Web Text)

Max Activating Token Index: 418

Text #1

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3657. Min Act: -0.1700

Data Index: 5338080 (Open Web Text)

Max Activating Token Index: 65

Text #2

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3639. Min Act: -0.1700

Data Index: 5507387 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3641. Min Act: -0.1700

Data Index: 3181117 (Open Web Text)

Max Activating Token Index: 352

Text #4

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3713. Min Act: -0.1700

Data Index: 4760169 (Open Web Text)

Max Activating Token Index: 81

Text #5

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3642. Min Act: -0.1700

Data Index: 58732 (Open Web Text)

Max Activating Token Index: 826

Text #6

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3624. Min Act: -0.1700

Data Index: 7900879 (Open Web Text)

Max Activating Token Index: 736

Text #7

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3387. Min Act: -0.1700

Data Index: 4925562 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3448. Min Act: -0.1700

Data Index: 2595923 (Open Web Text)

Max Activating Token Index: 624

Text #9

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3373. Min Act: -0.1700

Data Index: 1349310 (Open Web Text)

Max Activating Token Index: 144

Text #10

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3437. Min Act: -0.1700

Data Index: 3930817 (Open Web Text)

Max Activating Token Index: 86

Text #11

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3129. Min Act: -0.1700

Data Index: 4364612 (Open Web Text)

Max Activating Token Index: 771

Text #12

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.2902. Min Act: -0.1700

Data Index: 4331120 (Open Web Text)

Max Activating Token Index: 74

Text #13

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3184. Min Act: -0.1700

Data Index: 4169840 (Open Web Text)

Max Activating Token Index: 222

Text #14

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3111. Min Act: -0.1700

Data Index: 2138056 (Open Web Text)

Max Activating Token Index: 359

Text #15

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.3257. Min Act: -0.1700

Data Index: 6274481 (Open Web Text)

Max Activating Token Index: 645

Text #16

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.2768. Min Act: -0.1700

Data Index: 7850582 (Open Web Text)

Max Activating Token Index: 481

Text #17

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.2851. Min Act: -0.1700

Data Index: 5547879 (Open Web Text)

Max Activating Token Index: 178

Text #18

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.2236. Min Act: -0.1700

Data Index: 4269751 (Open Web Text)

Max Activating Token Index: 289

Text #19

Max Range: 4.4006. Min Range: -4.4006

Max Act: 4.2521. Min Act: -0.1700

Data Index: 881382 (Open Web Text)

Max Activating Token Index: 649