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

Dataset: Open Web Text

Neuron 2244 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: 2.3015. Min Range: -2.3015

Max Act: 2.3015. Min Act: -0.1700

Data Index: 2736333 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.2587. Min Act: -0.1700

Data Index: 4325792 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.2233. Min Act: -0.1700

Data Index: 3864610 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.2357. Min Act: -0.1700

Data Index: 8396618 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.2374. Min Act: -0.1700

Data Index: 66939 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.2248. Min Act: -0.1700

Data Index: 6445734 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.2179. Min Act: -0.1700

Data Index: 615684 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.2271. Min Act: -0.1700

Data Index: 6497450 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.2230. Min Act: -0.1700

Data Index: 3680118 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.2277. Min Act: -0.1700

Data Index: 8552474 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.1946. Min Act: -0.1700

Data Index: 4198148 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.2025. Min Act: -0.1700

Data Index: 1893054 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.1798. Min Act: -0.1700

Data Index: 7434324 (Open Web Text)

Max Activating Token Index: 56

Text #13

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.1660. Min Act: -0.1700

Data Index: 5758384 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.1565. Min Act: -0.1700

Data Index: 5927374 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.1711. Min Act: -0.1700

Data Index: 6991652 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.1650. Min Act: -0.1700

Data Index: 6171627 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.1616. Min Act: -0.1700

Data Index: 6248418 (Open Web Text)

Max Activating Token Index: 249

Text #18

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.1605. Min Act: -0.1700

Data Index: 6409721 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.1582. Min Act: -0.1700

Data Index: 3001052 (Open Web Text)

Max Activating Token Index: 10