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

Dataset: Open Web Text

Neuron 22 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: 3.4610. Min Range: -3.4610

Max Act: 3.4610. Min Act: -0.1700

Data Index: 7940749 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.3278. Min Act: -0.1700

Data Index: 2122976 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.3125. Min Act: -0.1700

Data Index: 6682245 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2906. Min Act: -0.1700

Data Index: 1168171 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2894. Min Act: -0.1700

Data Index: 993905 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2868. Min Act: -0.1700

Data Index: 3141053 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2775. Min Act: -0.1700

Data Index: 6814737 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2864. Min Act: -0.1700

Data Index: 578471 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2846. Min Act: -0.1700

Data Index: 7662172 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2749. Min Act: -0.1700

Data Index: 2524200 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2812. Min Act: -0.1700

Data Index: 8783770 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2862. Min Act: -0.1700

Data Index: 2310441 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2686. Min Act: -0.1700

Data Index: 239861 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2624. Min Act: -0.1700

Data Index: 7210112 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2700. Min Act: -0.1700

Data Index: 2554230 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2650. Min Act: -0.1700

Data Index: 5854386 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2669. Min Act: -0.1700

Data Index: 8475804 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2747. Min Act: -0.1700

Data Index: 5492520 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2552. Min Act: -0.1700

Data Index: 1657523 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.4610. Min Range: -3.4610

Max Act: 3.2578. Min Act: -0.1700

Data Index: 2385993 (Open Web Text)

Max Activating Token Index: 4