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

Dataset: Open Web Text

Neuron 300 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: 3.7210. Min Range: -3.7210

Max Act: 3.7210. Min Act: -0.1700

Data Index: 1005480 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.7167. Min Act: -0.1700

Data Index: 6535735 (Open Web Text)

Max Activating Token Index: 568

Text #2

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6868. Min Act: -0.1700

Data Index: 7191162 (Open Web Text)

Max Activating Token Index: 181

Text #3

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6834. Min Act: -0.1700

Data Index: 2926636 (Open Web Text)

Max Activating Token Index: 686

Text #4

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6185. Min Act: -0.1700

Data Index: 884937 (Open Web Text)

Max Activating Token Index: 930

Text #5

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6271. Min Act: -0.1700

Data Index: 5439831 (Open Web Text)

Max Activating Token Index: 139

Text #6

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6489. Min Act: -0.1700

Data Index: 2662723 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6544. Min Act: -0.1700

Data Index: 1658676 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6738. Min Act: -0.1700

Data Index: 7835668 (Open Web Text)

Max Activating Token Index: 701

Text #9

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6193. Min Act: -0.1700

Data Index: 5379519 (Open Web Text)

Max Activating Token Index: 158

Text #10

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6286. Min Act: -0.1700

Data Index: 6096056 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6071. Min Act: -0.1700

Data Index: 4154532 (Open Web Text)

Max Activating Token Index: 178

Text #12

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6286. Min Act: -0.1700

Data Index: 950249 (Open Web Text)

Max Activating Token Index: 68

Text #13

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6141. Min Act: -0.1700

Data Index: 5281684 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.5965. Min Act: -0.1700

Data Index: 388967 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6004. Min Act: -0.1700

Data Index: 6544198 (Open Web Text)

Max Activating Token Index: 298

Text #16

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6046. Min Act: -0.1700

Data Index: 3618241 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6012. Min Act: -0.1700

Data Index: 2306807 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6063. Min Act: -0.1700

Data Index: 3210921 (Open Web Text)

Max Activating Token Index: 675

Text #19

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6171. Min Act: -0.1700

Data Index: 7915297 (Open Web Text)

Max Activating Token Index: 854