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

Dataset: Open Web Text

Neuron 1670 in Layer 3

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: 4.0575. Min Range: -4.0575

Max Act: 4.0575. Min Act: -0.1700

Data Index: 6587683 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.7307. Min Act: -0.1700

Data Index: 1372581 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.6798. Min Act: -0.1700

Data Index: 3849527 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.6593. Min Act: -0.1700

Data Index: 4958760 (Open Web Text)

Max Activating Token Index: 36

Text #4

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.5575. Min Act: -0.1700

Data Index: 3310929 (Open Web Text)

Max Activating Token Index: 89

Text #5

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.5199. Min Act: -0.1700

Data Index: 8451142 (Open Web Text)

Max Activating Token Index: 93

Text #6

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.5297. Min Act: -0.1700

Data Index: 6447338 (Open Web Text)

Max Activating Token Index: 98

Text #7

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.5253. Min Act: -0.1700

Data Index: 483701 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4968. Min Act: -0.1700

Data Index: 6687937 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4295. Min Act: -0.1700

Data Index: 66858 (Open Web Text)

Max Activating Token Index: 84

Text #10

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4639. Min Act: -0.1700

Data Index: 3337128 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4682. Min Act: -0.1700

Data Index: 4270633 (Open Web Text)

Max Activating Token Index: 139

Text #12

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4843. Min Act: -0.1700

Data Index: 5929669 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4977. Min Act: -0.1700

Data Index: 3538099 (Open Web Text)

Max Activating Token Index: 140

Text #14

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4699. Min Act: -0.1700

Data Index: 6827644 (Open Web Text)

Max Activating Token Index: 144

Text #15

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4617. Min Act: -0.1700

Data Index: 3190621 (Open Web Text)

Max Activating Token Index: 211

Text #16

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4382. Min Act: -0.1700

Data Index: 6966405 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4422. Min Act: -0.1700

Data Index: 8480392 (Open Web Text)

Max Activating Token Index: 439

Text #18

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4022. Min Act: -0.1700

Data Index: 2748968 (Open Web Text)

Max Activating Token Index: 142

Text #19

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.3832. Min Act: -0.1700

Data Index: 5469122 (Open Web Text)

Max Activating Token Index: 19