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

Dataset: Open Web Text

Neuron 2788 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: 3.9935. Min Range: -3.9935

Max Act: 3.9935. Min Act: -0.1700

Data Index: 977837 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.9863. Min Act: -0.1700

Data Index: 6537642 (Open Web Text)

Max Activating Token Index: 359

Text #2

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.9228. Min Act: -0.1700

Data Index: 1211565 (Open Web Text)

Max Activating Token Index: 210

Text #3

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.9159. Min Act: -0.1700

Data Index: 8165724 (Open Web Text)

Max Activating Token Index: 263

Text #4

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.9199. Min Act: -0.1700

Data Index: 3773546 (Open Web Text)

Max Activating Token Index: 151

Text #5

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.9246. Min Act: -0.1700

Data Index: 7885847 (Open Web Text)

Max Activating Token Index: 740

Text #6

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.9185. Min Act: -0.1700

Data Index: 7044362 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.9100. Min Act: -0.1700

Data Index: 1773854 (Open Web Text)

Max Activating Token Index: 760

Text #8

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.9238. Min Act: -0.1700

Data Index: 2914063 (Open Web Text)

Max Activating Token Index: 75

Text #9

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.9038. Min Act: -0.1700

Data Index: 6513483 (Open Web Text)

Max Activating Token Index: 186

Text #10

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.8904. Min Act: -0.1700

Data Index: 4780293 (Open Web Text)

Max Activating Token Index: 743

Text #11

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.8870. Min Act: -0.1700

Data Index: 1122105 (Open Web Text)

Max Activating Token Index: 174

Text #12

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.9048. Min Act: -0.1700

Data Index: 4458240 (Open Web Text)

Max Activating Token Index: 165

Text #13

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.8548. Min Act: -0.1700

Data Index: 2341096 (Open Web Text)

Max Activating Token Index: 588

Text #14

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.8458. Min Act: -0.1700

Data Index: 7254270 (Open Web Text)

Max Activating Token Index: 911

Text #15

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.8432. Min Act: -0.1700

Data Index: 3871722 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.8782. Min Act: -0.1700

Data Index: 2146388 (Open Web Text)

Max Activating Token Index: 147

Text #17

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.8651. Min Act: -0.1700

Data Index: 4516533 (Open Web Text)

Max Activating Token Index: 1005

Text #18

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.8065. Min Act: -0.1700

Data Index: 23953 (Open Web Text)

Max Activating Token Index: 179

Text #19

Max Range: 3.9935. Min Range: -3.9935

Max Act: 3.8162. Min Act: -0.1700

Data Index: 1995238 (Open Web Text)

Max Activating Token Index: 903