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

Dataset: Open Web Text

Neuron 1504 in Layer 0

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: 5.6774. Min Range: -5.6774

Max Act: 5.6774. Min Act: -0.1700

Data Index: 7825188 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6640. Min Act: -0.1700

Data Index: 897319 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6730. Min Act: -0.1700

Data Index: 8374652 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6688. Min Act: -0.1700

Data Index: 4346101 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6685. Min Act: -0.1700

Data Index: 4433374 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6559. Min Act: -0.1700

Data Index: 1028519 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6364. Min Act: -0.1700

Data Index: 967126 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6132. Min Act: -0.1700

Data Index: 8605305 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6398. Min Act: -0.1700

Data Index: 1297771 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6067. Min Act: -0.1698

Data Index: 3928092 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6064. Min Act: -0.1700

Data Index: 6833989 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6264. Min Act: -0.1700

Data Index: 8612651 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6063. Min Act: -0.1700

Data Index: 2892673 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6163. Min Act: -0.1700

Data Index: 5932376 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6299. Min Act: -0.1700

Data Index: 4608754 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.6150. Min Act: -0.1700

Data Index: 7647758 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.5897. Min Act: -0.1700

Data Index: 6254521 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.5755. Min Act: -0.1700

Data Index: 6998660 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.5906. Min Act: -0.1699

Data Index: 592912 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.6774. Min Range: -5.6774

Max Act: 5.5990. Min Act: -0.1700

Data Index: 7374391 (Open Web Text)

Max Activating Token Index: 3