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

Dataset: Open Web Text

Neuron 1451 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: 5.6856. Min Range: -5.6856

Max Act: 5.6856. Min Act: -0.1700

Data Index: 4130824 (Open Web Text)

Max Activating Token Index: 156

Text #1

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.5881. Min Act: -0.1699

Data Index: 3052505 (Open Web Text)

Max Activating Token Index: 294

Text #2

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.5212. Min Act: -0.1700

Data Index: 7611462 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.5656. Min Act: -0.1700

Data Index: 3478585 (Open Web Text)

Max Activating Token Index: 175

Text #4

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.5381. Min Act: -0.1700

Data Index: 3451107 (Open Web Text)

Max Activating Token Index: 244

Text #5

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.4377. Min Act: -0.1700

Data Index: 951678 (Open Web Text)

Max Activating Token Index: 123

Text #6

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.4476. Min Act: -0.1700

Data Index: 4031999 (Open Web Text)

Max Activating Token Index: 119

Text #7

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.5397. Min Act: -0.1700

Data Index: 252304 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.3929. Min Act: -0.1698

Data Index: 4755260 (Open Web Text)

Max Activating Token Index: 587

Text #9

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.4898. Min Act: -0.1700

Data Index: 6964121 (Open Web Text)

Max Activating Token Index: 692

Text #10

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.4759. Min Act: -0.1700

Data Index: 1340367 (Open Web Text)

Max Activating Token Index: 116

Text #11

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.2312. Min Act: -0.1700

Data Index: 1151621 (Open Web Text)

Max Activating Token Index: 610

Text #12

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.2354. Min Act: -0.1700

Data Index: 6639147 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.3478. Min Act: -0.1700

Data Index: 2904690 (Open Web Text)

Max Activating Token Index: 599

Text #14

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.4505. Min Act: -0.1700

Data Index: 8567666 (Open Web Text)

Max Activating Token Index: 286

Text #15

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.2705. Min Act: -0.1700

Data Index: 1973635 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.3591. Min Act: -0.1700

Data Index: 4508124 (Open Web Text)

Max Activating Token Index: 664

Text #17

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.3210. Min Act: -0.1700

Data Index: 5504704 (Open Web Text)

Max Activating Token Index: 453

Text #18

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.3320. Min Act: -0.1700

Data Index: 6143843 (Open Web Text)

Max Activating Token Index: 688

Text #19

Max Range: 5.6856. Min Range: -5.6856

Max Act: 5.3228. Min Act: -0.1700

Data Index: 2430956 (Open Web Text)

Max Activating Token Index: 830