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

Dataset: Open Web Text

Neuron 1194 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: 1.6369. Min Range: -1.6369

Max Act: 1.6364. Min Act: -0.1700

Data Index: 6702587 (Open Web Text)

Max Activating Token Index: 947

Text #1

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6250. Min Act: -0.1700

Data Index: 1963776 (Open Web Text)

Max Activating Token Index: 895

Text #2

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6369. Min Act: -0.1700

Data Index: 5377131 (Open Web Text)

Max Activating Token Index: 376

Text #3

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6070. Min Act: -0.1700

Data Index: 8572901 (Open Web Text)

Max Activating Token Index: 656

Text #4

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6146. Min Act: -0.1700

Data Index: 8247163 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6144. Min Act: -0.1700

Data Index: 4213823 (Open Web Text)

Max Activating Token Index: 834

Text #6

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6221. Min Act: -0.1700

Data Index: 92276 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6049. Min Act: -0.1700

Data Index: 250606 (Open Web Text)

Max Activating Token Index: 871

Text #8

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6051. Min Act: -0.1700

Data Index: 4217458 (Open Web Text)

Max Activating Token Index: 500

Text #9

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6137. Min Act: -0.1700

Data Index: 1508256 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6051. Min Act: -0.1700

Data Index: 5372079 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6005. Min Act: -0.1700

Data Index: 8281239 (Open Web Text)

Max Activating Token Index: 633

Text #12

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.6035. Min Act: -0.1700

Data Index: 8293771 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.5906. Min Act: -0.1700

Data Index: 1018677 (Open Web Text)

Max Activating Token Index: 302

Text #14

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.5996. Min Act: -0.1700

Data Index: 1064139 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.5910. Min Act: -0.1700

Data Index: 2336543 (Open Web Text)

Max Activating Token Index: 946

Text #16

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.5977. Min Act: -0.1700

Data Index: 3971827 (Open Web Text)

Max Activating Token Index: 355

Text #17

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.5943. Min Act: -0.1700

Data Index: 6209691 (Open Web Text)

Max Activating Token Index: 534

Text #18

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.5937. Min Act: -0.1700

Data Index: 7058495 (Open Web Text)

Max Activating Token Index: 384

Text #19

Max Range: 1.6369. Min Range: -1.6369

Max Act: 1.5822. Min Act: -0.1700

Data Index: 6495005 (Open Web Text)

Max Activating Token Index: 881