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

Dataset: Open Web Text

Neuron 705 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: 1.3545. Min Range: -1.3545

Max Act: 1.3478. Min Act: -0.1700

Data Index: 4555089 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3545. Min Act: -0.1700

Data Index: 1227791 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3298. Min Act: -0.1700

Data Index: 5455922 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3297. Min Act: -0.1700

Data Index: 8066608 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3401. Min Act: -0.1700

Data Index: 5762674 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3387. Min Act: -0.1700

Data Index: 6340007 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3387. Min Act: -0.1700

Data Index: 6751299 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3230. Min Act: -0.1700

Data Index: 8107248 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3112. Min Act: -0.1700

Data Index: 5609283 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3147. Min Act: -0.1700

Data Index: 3793557 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3036. Min Act: -0.1700

Data Index: 1872250 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2976. Min Act: -0.1700

Data Index: 4354904 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2942. Min Act: -0.1700

Data Index: 7118887 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3052. Min Act: -0.1700

Data Index: 6978683 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2976. Min Act: -0.1700

Data Index: 6341367 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2995. Min Act: -0.1700

Data Index: 5717077 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2976. Min Act: -0.1700

Data Index: 3252680 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2943. Min Act: -0.1700

Data Index: 3064984 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2947. Min Act: -0.1700

Data Index: 4942098 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2915. Min Act: -0.1700

Data Index: 1088346 (Open Web Text)

Max Activating Token Index: 3