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

Dataset: Open Web Text

Neuron 1496 in Layer 0

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: 4.7154. Min Range: -4.7154

Max Act: 4.7154. Min Act: -0.1700

Data Index: 7926210 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6531. Min Act: -0.1700

Data Index: 2183479 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6596. Min Act: -0.1700

Data Index: 3604760 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6284. Min Act: -0.1700

Data Index: 5485170 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6170. Min Act: -0.1700

Data Index: 3705872 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6405. Min Act: -0.1700

Data Index: 3597094 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6376. Min Act: -0.1700

Data Index: 1427113 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6133. Min Act: -0.1700

Data Index: 6306200 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6255. Min Act: -0.1700

Data Index: 751642 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6405. Min Act: -0.1700

Data Index: 2323442 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6373. Min Act: -0.1700

Data Index: 4319610 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6232. Min Act: -0.1700

Data Index: 6980548 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6337. Min Act: -0.1700

Data Index: 4760404 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6211. Min Act: -0.1700

Data Index: 1895560 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6211. Min Act: -0.1700

Data Index: 4456396 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6195. Min Act: -0.1700

Data Index: 8252635 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.5957. Min Act: -0.1700

Data Index: 6017593 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.5791. Min Act: -0.1700

Data Index: 6145554 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.5876. Min Act: -0.1700

Data Index: 289572 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.7154. Min Range: -4.7154

Max Act: 4.6112. Min Act: -0.1700

Data Index: 4373397 (Open Web Text)

Max Activating Token Index: 3