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

Dataset: Open Web Text

Neuron 1939 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: 7.0610. Min Range: -7.0610

Max Act: 7.0260. Min Act: -0.1700

Data Index: 2228117 (Open Web Text)

Max Activating Token Index: 112

Text #1

Max Range: 7.0610. Min Range: -7.0610

Max Act: 7.0610. Min Act: -0.1700

Data Index: 5071666 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 7.0610. Min Range: -7.0610

Max Act: 7.0226. Min Act: -0.1700

Data Index: 6237313 (Open Web Text)

Max Activating Token Index: 44

Text #3

Max Range: 7.0610. Min Range: -7.0610

Max Act: 7.0474. Min Act: -0.1700

Data Index: 715054 (Open Web Text)

Max Activating Token Index: 57

Text #4

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.9498. Min Act: -0.1700

Data Index: 8480859 (Open Web Text)

Max Activating Token Index: 57

Text #5

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.9708. Min Act: -0.1700

Data Index: 8079459 (Open Web Text)

Max Activating Token Index: 34

Text #6

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.9719. Min Act: -0.1700

Data Index: 965390 (Open Web Text)

Max Activating Token Index: 53

Text #7

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.8864. Min Act: -0.1700

Data Index: 4302137 (Open Web Text)

Max Activating Token Index: 62

Text #8

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.9215. Min Act: -0.1700

Data Index: 3003807 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.9050. Min Act: -0.1700

Data Index: 7569300 (Open Web Text)

Max Activating Token Index: 96

Text #10

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.8780. Min Act: -0.1700

Data Index: 7509422 (Open Web Text)

Max Activating Token Index: 28

Text #11

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.8784. Min Act: -0.1700

Data Index: 7467705 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.9251. Min Act: -0.1700

Data Index: 7316726 (Open Web Text)

Max Activating Token Index: 187

Text #13

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.8951. Min Act: -0.1700

Data Index: 6239179 (Open Web Text)

Max Activating Token Index: 88

Text #14

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.8719. Min Act: -0.1700

Data Index: 2049811 (Open Web Text)

Max Activating Token Index: 114

Text #15

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.9115. Min Act: -0.1700

Data Index: 1707481 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.8883. Min Act: -0.1700

Data Index: 4905372 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.8874. Min Act: -0.1700

Data Index: 1698700 (Open Web Text)

Max Activating Token Index: 45

Text #18

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.8818. Min Act: -0.1700

Data Index: 357503 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 7.0610. Min Range: -7.0610

Max Act: 6.8455. Min Act: -0.1700

Data Index: 3094556 (Open Web Text)

Max Activating Token Index: 383