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

Dataset: Open Web Text

Neuron 1164 in Layer 1

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: 1.8396. Min Range: -1.8396

Max Act: 1.8396. Min Act: -0.1677

Data Index: 4015911 (Open Web Text)

Max Activating Token Index: 846

Text #1

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.8336. Min Act: -0.1698

Data Index: 7301923 (Open Web Text)

Max Activating Token Index: 114

Text #2

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.8341. Min Act: -0.1700

Data Index: 4193288 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.8208. Min Act: -0.1700

Data Index: 6611039 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.8116. Min Act: -0.1700

Data Index: 3378870 (Open Web Text)

Max Activating Token Index: 89

Text #5

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.8021. Min Act: -0.1698

Data Index: 4135515 (Open Web Text)

Max Activating Token Index: 257

Text #6

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.8026. Min Act: -0.1699

Data Index: 604870 (Open Web Text)

Max Activating Token Index: 420

Text #7

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7962. Min Act: -0.1700

Data Index: 7306268 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7872. Min Act: -0.1700

Data Index: 408550 (Open Web Text)

Max Activating Token Index: 148

Text #9

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7910. Min Act: -0.1700

Data Index: 2890575 (Open Web Text)

Max Activating Token Index: 97

Text #10

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7870. Min Act: -0.1700

Data Index: 3520669 (Open Web Text)

Max Activating Token Index: 52

Text #11

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7865. Min Act: -0.1688

Data Index: 552831 (Open Web Text)

Max Activating Token Index: 173

Text #12

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7907. Min Act: -0.1700

Data Index: 5413377 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7847. Min Act: -0.1700

Data Index: 2949326 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7837. Min Act: -0.1700

Data Index: 4794441 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7798. Min Act: -0.1700

Data Index: 4444251 (Open Web Text)

Max Activating Token Index: 74

Text #16

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7828. Min Act: -0.1700

Data Index: 3719325 (Open Web Text)

Max Activating Token Index: 153

Text #17

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7715. Min Act: -0.1700

Data Index: 2380851 (Open Web Text)

Max Activating Token Index: 764

Text #18

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7643. Min Act: -0.1699

Data Index: 5060796 (Open Web Text)

Max Activating Token Index: 115

Text #19

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7577. Min Act: -0.1700

Data Index: 3346186 (Open Web Text)

Max Activating Token Index: 702