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

Dataset: Open Web Text

Neuron 1743 in Layer 5

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: 1.6403. Min Range: -1.6403

Max Act: 1.6403. Min Act: -0.1700

Data Index: 2807039 (Open Web Text)

Max Activating Token Index: 123

Text #1

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.5274. Min Act: -0.1700

Data Index: 3899403 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.5010. Min Act: -0.1700

Data Index: 52809 (Open Web Text)

Max Activating Token Index: 118

Text #3

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4922. Min Act: -0.1700

Data Index: 4431004 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4923. Min Act: -0.1700

Data Index: 5852522 (Open Web Text)

Max Activating Token Index: 131

Text #5

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4602. Min Act: -0.1700

Data Index: 264595 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4538. Min Act: -0.1700

Data Index: 4805685 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4416. Min Act: -0.1700

Data Index: 3408290 (Open Web Text)

Max Activating Token Index: 126

Text #8

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4387. Min Act: -0.1700

Data Index: 7884075 (Open Web Text)

Max Activating Token Index: 118

Text #9

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4415. Min Act: -0.1700

Data Index: 2783634 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4259. Min Act: -0.1700

Data Index: 4245163 (Open Web Text)

Max Activating Token Index: 126

Text #11

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4191. Min Act: -0.1700

Data Index: 191308 (Open Web Text)

Max Activating Token Index: 64

Text #12

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4206. Min Act: -0.1700

Data Index: 4121909 (Open Web Text)

Max Activating Token Index: 149

Text #13

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4111. Min Act: -0.1700

Data Index: 5445235 (Open Web Text)

Max Activating Token Index: 140

Text #14

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4104. Min Act: -0.1700

Data Index: 1721771 (Open Web Text)

Max Activating Token Index: 148

Text #15

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4110. Min Act: -0.1700

Data Index: 6798511 (Open Web Text)

Max Activating Token Index: 97

Text #16

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4080. Min Act: -0.1700

Data Index: 4003619 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4040. Min Act: -0.1700

Data Index: 1679440 (Open Web Text)

Max Activating Token Index: 133

Text #18

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4013. Min Act: -0.1700

Data Index: 6504068 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.3968. Min Act: -0.1700

Data Index: 597928 (Open Web Text)

Max Activating Token Index: 114