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

Dataset: Open Web Text

Neuron 878 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: 4.2154. Min Range: -4.2154

Max Act: 4.2154. Min Act: -0.1700

Data Index: 6000890 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.2154. Min Range: -4.2154

Max Act: 4.2065. Min Act: -0.1700

Data Index: 1341138 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.2154. Min Range: -4.2154

Max Act: 4.0844. Min Act: -0.1700

Data Index: 7482688 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 4.2154. Min Range: -4.2154

Max Act: 4.0750. Min Act: -0.1700

Data Index: 2876403 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.2154. Min Range: -4.2154

Max Act: 4.0232. Min Act: -0.1700

Data Index: 2189003 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.2154. Min Range: -4.2154

Max Act: 4.0269. Min Act: -0.1700

Data Index: 110962 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9982. Min Act: -0.1700

Data Index: 6326374 (Open Web Text)

Max Activating Token Index: 769

Text #7

Max Range: 4.2154. Min Range: -4.2154

Max Act: 4.0155. Min Act: -0.1700

Data Index: 7713683 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9738. Min Act: -0.1700

Data Index: 1625259 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9673. Min Act: -0.1700

Data Index: 2084150 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9897. Min Act: -0.1700

Data Index: 3936581 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9796. Min Act: -0.1700

Data Index: 3892750 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9661. Min Act: -0.1700

Data Index: 5660036 (Open Web Text)

Max Activating Token Index: 140

Text #13

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9631. Min Act: -0.1700

Data Index: 4625046 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9727. Min Act: -0.1700

Data Index: 7935877 (Open Web Text)

Max Activating Token Index: 884

Text #15

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9706. Min Act: -0.1700

Data Index: 6794461 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9791. Min Act: -0.1700

Data Index: 6662744 (Open Web Text)

Max Activating Token Index: 23

Text #17

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9359. Min Act: -0.1700

Data Index: 5933187 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9378. Min Act: -0.1700

Data Index: 884554 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.2154. Min Range: -4.2154

Max Act: 3.9398. Min Act: -0.1700

Data Index: 1580873 (Open Web Text)

Max Activating Token Index: 18