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

Dataset: Open Web Text

Neuron 2810 in Layer 4

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: 2.1194. Min Range: -2.1194

Max Act: 2.1194. Min Act: -0.1700

Data Index: 74225 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0840. Min Act: -0.1700

Data Index: 637857 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0540. Min Act: -0.1700

Data Index: 5435324 (Open Web Text)

Max Activating Token Index: 57

Text #3

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0194. Min Act: -0.1700

Data Index: 1871127 (Open Web Text)

Max Activating Token Index: 98

Text #4

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0177. Min Act: -0.1700

Data Index: 1080605 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0215. Min Act: -0.1700

Data Index: 1224441 (Open Web Text)

Max Activating Token Index: 327

Text #6

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0143. Min Act: -0.1700

Data Index: 2499054 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 2.1194. Min Range: -2.1194

Max Act: 1.9944. Min Act: -0.1700

Data Index: 5079576 (Open Web Text)

Max Activating Token Index: 288

Text #8

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0103. Min Act: -0.1700

Data Index: 4088216 (Open Web Text)

Max Activating Token Index: 141

Text #9

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0077. Min Act: -0.1700

Data Index: 5077771 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0068. Min Act: -0.1700

Data Index: 5022386 (Open Web Text)

Max Activating Token Index: 162

Text #11

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0035. Min Act: -0.1700

Data Index: 8662377 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0114. Min Act: -0.1700

Data Index: 5514663 (Open Web Text)

Max Activating Token Index: 248

Text #13

Max Range: 2.1194. Min Range: -2.1194

Max Act: 2.0008. Min Act: -0.1700

Data Index: 4656350 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 2.1194. Min Range: -2.1194

Max Act: 1.9880. Min Act: -0.1700

Data Index: 6517876 (Open Web Text)

Max Activating Token Index: 35

Text #15

Max Range: 2.1194. Min Range: -2.1194

Max Act: 1.9796. Min Act: -0.1700

Data Index: 2246536 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 2.1194. Min Range: -2.1194

Max Act: 1.9752. Min Act: -0.1700

Data Index: 4904488 (Open Web Text)

Max Activating Token Index: 288

Text #17

Max Range: 2.1194. Min Range: -2.1194

Max Act: 1.9688. Min Act: -0.1700

Data Index: 2205407 (Open Web Text)

Max Activating Token Index: 201

Text #18

Max Range: 2.1194. Min Range: -2.1194

Max Act: 1.9892. Min Act: -0.1700

Data Index: 4655080 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 2.1194. Min Range: -2.1194

Max Act: 1.9802. Min Act: -0.1700

Data Index: 2320613 (Open Web Text)

Max Activating Token Index: 290