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

Dataset: Open Web Text

Neuron 706 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: 1.6829. Min Range: -1.6829

Max Act: 1.6829. Min Act: -0.1700

Data Index: 792397 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.6614. Min Act: -0.1700

Data Index: 604664 (Open Web Text)

Max Activating Token Index: 62

Text #2

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.6256. Min Act: -0.1700

Data Index: 1505300 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5986. Min Act: -0.1700

Data Index: 8285564 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5968. Min Act: -0.1700

Data Index: 1505307 (Open Web Text)

Max Activating Token Index: 83

Text #5

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5637. Min Act: -0.1700

Data Index: 1345858 (Open Web Text)

Max Activating Token Index: 82

Text #6

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5736. Min Act: -0.1700

Data Index: 5316251 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5468. Min Act: -0.1700

Data Index: 5935640 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5428. Min Act: -0.1700

Data Index: 555792 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5323. Min Act: -0.1700

Data Index: 1505301 (Open Web Text)

Max Activating Token Index: 73

Text #10

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5369. Min Act: -0.1700

Data Index: 127674 (Open Web Text)

Max Activating Token Index: 71

Text #11

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5070. Min Act: -0.1700

Data Index: 8249076 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5116. Min Act: -0.1700

Data Index: 5626238 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5141. Min Act: -0.1700

Data Index: 4384052 (Open Web Text)

Max Activating Token Index: 62

Text #14

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5114. Min Act: -0.1700

Data Index: 8444940 (Open Web Text)

Max Activating Token Index: 93

Text #15

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.4874. Min Act: -0.1700

Data Index: 4630656 (Open Web Text)

Max Activating Token Index: 92

Text #16

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.4923. Min Act: -0.1700

Data Index: 4812661 (Open Web Text)

Max Activating Token Index: 88

Text #17

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.4989. Min Act: -0.1700

Data Index: 4442506 (Open Web Text)

Max Activating Token Index: 73

Text #18

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.5042. Min Act: -0.1700

Data Index: 2175850 (Open Web Text)

Max Activating Token Index: 114

Text #19

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.4941. Min Act: -0.1700

Data Index: 7043979 (Open Web Text)

Max Activating Token Index: 75