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

Dataset: Open Web Text

Neuron 2727 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: 1.7383. Min Range: -1.7383

Max Act: 1.7383. Min Act: -0.1700

Data Index: 1188216 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6821. Min Act: -0.1700

Data Index: 6291008 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6892. Min Act: -0.1700

Data Index: 2733771 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6689. Min Act: -0.1700

Data Index: 1203877 (Open Web Text)

Max Activating Token Index: 104

Text #4

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6626. Min Act: -0.1700

Data Index: 867169 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6451. Min Act: -0.1700

Data Index: 597215 (Open Web Text)

Max Activating Token Index: 39

Text #6

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6391. Min Act: -0.1700

Data Index: 3072084 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6357. Min Act: -0.1700

Data Index: 6450752 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6309. Min Act: -0.1700

Data Index: 269096 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6321. Min Act: -0.1700

Data Index: 5365963 (Open Web Text)

Max Activating Token Index: 682

Text #10

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6170. Min Act: -0.1700

Data Index: 6681181 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6036. Min Act: -0.1700

Data Index: 1477541 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6017. Min Act: -0.1700

Data Index: 2632324 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6033. Min Act: -0.1700

Data Index: 39722 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5933. Min Act: -0.1700

Data Index: 3931014 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5932. Min Act: -0.1700

Data Index: 8654777 (Open Web Text)

Max Activating Token Index: 663

Text #16

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5900. Min Act: -0.1700

Data Index: 4660385 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5977. Min Act: -0.1700

Data Index: 7867961 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5943. Min Act: -0.1700

Data Index: 7780385 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5832. Min Act: -0.1700

Data Index: 3074111 (Open Web Text)

Max Activating Token Index: 14