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

Dataset: Open Web Text

Neuron 48 in Layer 2

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: 3.1186. Min Range: -3.1186

Max Act: 3.1186. Min Act: -0.1700

Data Index: 7424272 (Open Web Text)

Max Activating Token Index: 917

Text #1

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9950. Min Act: -0.1700

Data Index: 8054110 (Open Web Text)

Max Activating Token Index: 928

Text #2

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9794. Min Act: -0.1700

Data Index: 7155678 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9901. Min Act: -0.1700

Data Index: 7776623 (Open Web Text)

Max Activating Token Index: 178

Text #4

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9519. Min Act: -0.1700

Data Index: 6350874 (Open Web Text)

Max Activating Token Index: 568

Text #5

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9564. Min Act: -0.1700

Data Index: 2139565 (Open Web Text)

Max Activating Token Index: 589

Text #6

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9253. Min Act: -0.1700

Data Index: 2982797 (Open Web Text)

Max Activating Token Index: 248

Text #7

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9332. Min Act: -0.1700

Data Index: 116174 (Open Web Text)

Max Activating Token Index: 125

Text #8

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9054. Min Act: -0.1700

Data Index: 344241 (Open Web Text)

Max Activating Token Index: 613

Text #9

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9209. Min Act: -0.1700

Data Index: 656593 (Open Web Text)

Max Activating Token Index: 757

Text #10

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8752. Min Act: -0.1700

Data Index: 3594316 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8858. Min Act: -0.1700

Data Index: 5989172 (Open Web Text)

Max Activating Token Index: 204

Text #12

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8761. Min Act: -0.1700

Data Index: 2939950 (Open Web Text)

Max Activating Token Index: 102

Text #13

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8738. Min Act: -0.1700

Data Index: 1643637 (Open Web Text)

Max Activating Token Index: 181

Text #14

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8647. Min Act: -0.1700

Data Index: 7698524 (Open Web Text)

Max Activating Token Index: 851

Text #15

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8746. Min Act: -0.1700

Data Index: 1149241 (Open Web Text)

Max Activating Token Index: 247

Text #16

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8819. Min Act: -0.1700

Data Index: 1643636 (Open Web Text)

Max Activating Token Index: 128

Text #17

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8711. Min Act: -0.1700

Data Index: 601419 (Open Web Text)

Max Activating Token Index: 427

Text #18

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8709. Min Act: -0.1700

Data Index: 1078310 (Open Web Text)

Max Activating Token Index: 61

Text #19

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8502. Min Act: -0.1700

Data Index: 784304 (Open Web Text)

Max Activating Token Index: 926