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

Dataset: Open Web Text

Neuron 2890 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: 3.8533. Min Range: -3.8533

Max Act: 3.8533. Min Act: -0.1700

Data Index: 7000932 (Open Web Text)

Max Activating Token Index: 192

Text #1

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.8378. Min Act: -0.1700

Data Index: 7000934 (Open Web Text)

Max Activating Token Index: 136

Text #2

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7934. Min Act: -0.1700

Data Index: 7000935 (Open Web Text)

Max Activating Token Index: 309

Text #3

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7584. Min Act: -0.1700

Data Index: 4093882 (Open Web Text)

Max Activating Token Index: 64

Text #4

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7623. Min Act: -0.1700

Data Index: 7000936 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7184. Min Act: -0.1700

Data Index: 3841464 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7238. Min Act: -0.1700

Data Index: 6501806 (Open Web Text)

Max Activating Token Index: 557

Text #7

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7284. Min Act: -0.1700

Data Index: 8418700 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7227. Min Act: -0.1700

Data Index: 1761601 (Open Web Text)

Max Activating Token Index: 192

Text #9

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7236. Min Act: -0.1700

Data Index: 7000933 (Open Web Text)

Max Activating Token Index: 239

Text #10

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7064. Min Act: -0.1700

Data Index: 3630113 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.6974. Min Act: -0.1700

Data Index: 3606835 (Open Web Text)

Max Activating Token Index: 175

Text #12

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7137. Min Act: -0.1700

Data Index: 656028 (Open Web Text)

Max Activating Token Index: 114

Text #13

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.7001. Min Act: -0.1700

Data Index: 1066422 (Open Web Text)

Max Activating Token Index: 729

Text #14

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.6986. Min Act: -0.1700

Data Index: 2216205 (Open Web Text)

Max Activating Token Index: 112

Text #15

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.6923. Min Act: -0.1700

Data Index: 6250371 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.6890. Min Act: -0.1700

Data Index: 2835502 (Open Web Text)

Max Activating Token Index: 315

Text #17

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.6956. Min Act: -0.1700

Data Index: 2581189 (Open Web Text)

Max Activating Token Index: 595

Text #18

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.6517. Min Act: -0.1700

Data Index: 6820856 (Open Web Text)

Max Activating Token Index: 83

Text #19

Max Range: 3.8533. Min Range: -3.8533

Max Act: 3.6702. Min Act: -0.1700

Data Index: 4661392 (Open Web Text)

Max Activating Token Index: 91