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

Dataset: Open Web Text

Neuron 1536 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: 2.9852. Min Range: -2.9852

Max Act: 2.9852. Min Act: -0.1700

Data Index: 3896290 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9569. Min Act: -0.1700

Data Index: 4031176 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9417. Min Act: -0.1700

Data Index: 4970752 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9359. Min Act: -0.1700

Data Index: 8732899 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9381. Min Act: -0.1700

Data Index: 8199352 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9283. Min Act: -0.1700

Data Index: 936489 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9214. Min Act: -0.1700

Data Index: 7827446 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9062. Min Act: -0.1700

Data Index: 1916318 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9062. Min Act: -0.1700

Data Index: 4576950 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9062. Min Act: -0.1700

Data Index: 3628599 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9097. Min Act: -0.1700

Data Index: 8218432 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9062. Min Act: -0.1700

Data Index: 2867912 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9062. Min Act: -0.1700

Data Index: 7128459 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9163. Min Act: -0.1700

Data Index: 7125584 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9062. Min Act: -0.1700

Data Index: 6714621 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.9062. Min Act: -0.1700

Data Index: 1040339 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.8880. Min Act: -0.1700

Data Index: 4082214 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.8946. Min Act: -0.1700

Data Index: 1466068 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.8880. Min Act: -0.1700

Data Index: 428109 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 2.9852. Min Range: -2.9852

Max Act: 2.8951. Min Act: -0.1700

Data Index: 4699718 (Open Web Text)

Max Activating Token Index: 15