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

Dataset: Open Web Text

Neuron 747 in Layer 2

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: 1.8856. Min Range: -1.8856

Max Act: 1.8856. Min Act: -0.1700

Data Index: 880325 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7732. Min Act: -0.1700

Data Index: 7036630 (Open Web Text)

Max Activating Token Index: 567

Text #2

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7506. Min Act: -0.1700

Data Index: 2827137 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7416. Min Act: -0.1700

Data Index: 1124823 (Open Web Text)

Max Activating Token Index: 791

Text #4

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7274. Min Act: -0.1700

Data Index: 1127430 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7274. Min Act: -0.1700

Data Index: 6425315 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7274. Min Act: -0.1700

Data Index: 2954446 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7274. Min Act: -0.1700

Data Index: 4156015 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7274. Min Act: -0.1700

Data Index: 6189567 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7369. Min Act: -0.1700

Data Index: 6924432 (Open Web Text)

Max Activating Token Index: 358

Text #10

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7366. Min Act: -0.1700

Data Index: 7341731 (Open Web Text)

Max Activating Token Index: 449

Text #11

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7150. Min Act: -0.1699

Data Index: 5565741 (Open Web Text)

Max Activating Token Index: 949

Text #12

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7185. Min Act: -0.1700

Data Index: 8524138 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7015. Min Act: -0.1700

Data Index: 3176986 (Open Web Text)

Max Activating Token Index: 547

Text #14

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.6969. Min Act: -0.1700

Data Index: 1298518 (Open Web Text)

Max Activating Token Index: 356

Text #15

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.6947. Min Act: -0.1700

Data Index: 6441859 (Open Web Text)

Max Activating Token Index: 460

Text #16

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.6923. Min Act: -0.1700

Data Index: 8055495 (Open Web Text)

Max Activating Token Index: 817

Text #17

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.6909. Min Act: -0.1700

Data Index: 2792612 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.6824. Min Act: -0.1700

Data Index: 1133996 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.6920. Min Act: -0.1700

Data Index: 2876956 (Open Web Text)

Max Activating Token Index: 419