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

Dataset: Open Web Text

Neuron 1020 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: 2.4849. Min Range: -2.4849

Max Act: 2.4849. Min Act: -0.1700

Data Index: 2033750 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.4311. Min Act: -0.1700

Data Index: 812122 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3835. Min Act: -0.1700

Data Index: 8508721 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3810. Min Act: -0.1700

Data Index: 7345093 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3473. Min Act: -0.1700

Data Index: 545873 (Open Web Text)

Max Activating Token Index: 276

Text #5

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3514. Min Act: -0.1700

Data Index: 3687587 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3457. Min Act: -0.1700

Data Index: 7375168 (Open Web Text)

Max Activating Token Index: 34

Text #7

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3256. Min Act: -0.1700

Data Index: 4898262 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3150. Min Act: -0.1700

Data Index: 2379502 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3259. Min Act: -0.1700

Data Index: 5834988 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3296. Min Act: -0.1700

Data Index: 3797552 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3140. Min Act: -0.1700

Data Index: 885306 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3022. Min Act: -0.1700

Data Index: 2013170 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3037. Min Act: -0.1700

Data Index: 7016497 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3046. Min Act: -0.1700

Data Index: 6785912 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3063. Min Act: -0.1700

Data Index: 5076369 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3070. Min Act: -0.1700

Data Index: 1791574 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.2880. Min Act: -0.1700

Data Index: 4838051 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.2956. Min Act: -0.1700

Data Index: 6157507 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 2.4849. Min Range: -2.4849

Max Act: 2.3014. Min Act: -0.1700

Data Index: 3989766 (Open Web Text)

Max Activating Token Index: 53