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

Dataset: Open Web Text

Neuron 1090 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: 3.5103. Min Range: -3.5103

Max Act: 3.5103. Min Act: -0.1700

Data Index: 5246730 (Open Web Text)

Max Activating Token Index: 279

Text #1

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3842. Min Act: -0.1700

Data Index: 1497634 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3965. Min Act: -0.1700

Data Index: 6643901 (Open Web Text)

Max Activating Token Index: 766

Text #3

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3849. Min Act: -0.1700

Data Index: 7223309 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3649. Min Act: -0.1700

Data Index: 2366624 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3700. Min Act: -0.1700

Data Index: 5977870 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3488. Min Act: -0.1700

Data Index: 2494283 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3564. Min Act: -0.1700

Data Index: 882373 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3367. Min Act: -0.1700

Data Index: 5161922 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3339. Min Act: -0.1700

Data Index: 916578 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3332. Min Act: -0.1700

Data Index: 8045232 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3249. Min Act: -0.1700

Data Index: 5816076 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3417. Min Act: -0.1700

Data Index: 5476605 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3188. Min Act: -0.1700

Data Index: 6000130 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3254. Min Act: -0.1700

Data Index: 535074 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3219. Min Act: -0.1700

Data Index: 2980017 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3222. Min Act: -0.1700

Data Index: 4861634 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3208. Min Act: -0.1700

Data Index: 2706732 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3199. Min Act: -0.1700

Data Index: 3756676 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3205. Min Act: -0.1700

Data Index: 7323059 (Open Web Text)

Max Activating Token Index: 3