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

Dataset: Open Web Text

Neuron 2876 in Layer 4

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: 2.3097. Min Range: -2.3097

Max Act: 2.3097. Min Act: -0.1700

Data Index: 945378 (Open Web Text)

Max Activating Token Index: 604

Text #1

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9317. Min Act: -0.1699

Data Index: 2350720 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9367. Min Act: -0.1700

Data Index: 216027 (Open Web Text)

Max Activating Token Index: 54

Text #3

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9371. Min Act: -0.1700

Data Index: 8244804 (Open Web Text)

Max Activating Token Index: 56

Text #4

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9270. Min Act: -0.1700

Data Index: 6253557 (Open Web Text)

Max Activating Token Index: 63

Text #5

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9243. Min Act: -0.1700

Data Index: 2184422 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9049. Min Act: -0.1700

Data Index: 2335801 (Open Web Text)

Max Activating Token Index: 84

Text #7

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9030. Min Act: -0.1700

Data Index: 2315219 (Open Web Text)

Max Activating Token Index: 95

Text #8

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9134. Min Act: -0.1700

Data Index: 459526 (Open Web Text)

Max Activating Token Index: 46

Text #9

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9129. Min Act: -0.1700

Data Index: 1018937 (Open Web Text)

Max Activating Token Index: 66

Text #10

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.8988. Min Act: -0.1700

Data Index: 322910 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9001. Min Act: -0.1698

Data Index: 6310389 (Open Web Text)

Max Activating Token Index: 88

Text #12

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.9001. Min Act: -0.1700

Data Index: 358130 (Open Web Text)

Max Activating Token Index: 88

Text #13

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.8947. Min Act: -0.1700

Data Index: 5299026 (Open Web Text)

Max Activating Token Index: 29

Text #14

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.8961. Min Act: -0.1700

Data Index: 1900698 (Open Web Text)

Max Activating Token Index: 37

Text #15

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.8947. Min Act: -0.1700

Data Index: 1737845 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.8997. Min Act: -0.1700

Data Index: 3687001 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.8964. Min Act: -0.1698

Data Index: 227386 (Open Web Text)

Max Activating Token Index: 36

Text #18

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.8957. Min Act: -0.1696

Data Index: 1543507 (Open Web Text)

Max Activating Token Index: 98

Text #19

Max Range: 2.3097. Min Range: -2.3097

Max Act: 1.8987. Min Act: -0.1699

Data Index: 204141 (Open Web Text)

Max Activating Token Index: 70