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

Dataset: Open Web Text

Neuron 2344 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: 4.1142. Min Range: -4.1142

Max Act: 4.1142. Min Act: -0.1700

Data Index: 4257335 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.1142. Min Range: -4.1142

Max Act: 4.0579. Min Act: -0.1700

Data Index: 5998438 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.8711. Min Act: -0.1700

Data Index: 1955008 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.8152. Min Act: -0.1700

Data Index: 5622424 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.8355. Min Act: -0.1700

Data Index: 458638 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.7988. Min Act: -0.1700

Data Index: 2336255 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.7637. Min Act: -0.1700

Data Index: 5553330 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.7791. Min Act: -0.1700

Data Index: 3280833 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.7364. Min Act: -0.1700

Data Index: 3063879 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.7373. Min Act: -0.1700

Data Index: 6922447 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.7212. Min Act: -0.1700

Data Index: 132084 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.7218. Min Act: -0.1700

Data Index: 453759 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.7206. Min Act: -0.1700

Data Index: 7518617 (Open Web Text)

Max Activating Token Index: 203

Text #13

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.7005. Min Act: -0.1700

Data Index: 2488543 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.7049. Min Act: -0.1700

Data Index: 5097866 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.6994. Min Act: -0.1700

Data Index: 3529256 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.6705. Min Act: -0.1700

Data Index: 2405668 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.6747. Min Act: -0.1700

Data Index: 216908 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.6638. Min Act: -0.1700

Data Index: 4108053 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 4.1142. Min Range: -4.1142

Max Act: 3.6694. Min Act: -0.1700

Data Index: 1970971 (Open Web Text)

Max Activating Token Index: 1023