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

Dataset: Open Web Text

Neuron 2142 in Layer 1

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: 5.6726. Min Range: -5.6726

Max Act: 5.6726. Min Act: -0.1700

Data Index: 2203990 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.6643. Min Act: -0.1700

Data Index: 2955715 (Open Web Text)

Max Activating Token Index: 178

Text #2

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.6299. Min Act: -0.1700

Data Index: 2244921 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.5835. Min Act: -0.1700

Data Index: 4843578 (Open Web Text)

Max Activating Token Index: 179

Text #4

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.5500. Min Act: -0.1700

Data Index: 7495306 (Open Web Text)

Max Activating Token Index: 92

Text #5

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.5139. Min Act: -0.1700

Data Index: 383457 (Open Web Text)

Max Activating Token Index: 136

Text #6

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.5135. Min Act: -0.1700

Data Index: 7241108 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.5265. Min Act: -0.1700

Data Index: 4523340 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4843. Min Act: -0.1700

Data Index: 3419338 (Open Web Text)

Max Activating Token Index: 259

Text #9

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.5034. Min Act: -0.1700

Data Index: 7099390 (Open Web Text)

Max Activating Token Index: 162

Text #10

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4468. Min Act: -0.1700

Data Index: 4846463 (Open Web Text)

Max Activating Token Index: 176

Text #11

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4874. Min Act: -0.1700

Data Index: 2016820 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4705. Min Act: -0.1700

Data Index: 8026743 (Open Web Text)

Max Activating Token Index: 184

Text #13

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4750. Min Act: -0.1700

Data Index: 2955714 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4482. Min Act: -0.1700

Data Index: 7489170 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4509. Min Act: -0.1700

Data Index: 512292 (Open Web Text)

Max Activating Token Index: 114

Text #16

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4307. Min Act: -0.1700

Data Index: 3683944 (Open Web Text)

Max Activating Token Index: 45

Text #17

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4231. Min Act: -0.1700

Data Index: 8195455 (Open Web Text)

Max Activating Token Index: 32

Text #18

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4402. Min Act: -0.1700

Data Index: 7349748 (Open Web Text)

Max Activating Token Index: 197

Text #19

Max Range: 5.6726. Min Range: -5.6726

Max Act: 5.4065. Min Act: -0.1700

Data Index: 76711 (Open Web Text)

Max Activating Token Index: 71