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

Dataset: Open Web Text

Neuron 2641 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: 3.3162. Min Range: -3.3162

Max Act: 3.3162. Min Act: -0.1700

Data Index: 4311390 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.2295. Min Act: -0.1700

Data Index: 402636 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1889. Min Act: -0.1700

Data Index: 3211530 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1622. Min Act: -0.1700

Data Index: 2905960 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1759. Min Act: -0.1700

Data Index: 1179233 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1661. Min Act: -0.1700

Data Index: 7632644 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1471. Min Act: -0.1700

Data Index: 4638331 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1360. Min Act: -0.1700

Data Index: 8580802 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1366. Min Act: -0.1700

Data Index: 3585319 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1435. Min Act: -0.1700

Data Index: 1089467 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1096. Min Act: -0.1700

Data Index: 4241806 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1310. Min Act: -0.1700

Data Index: 8350109 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1297. Min Act: -0.1700

Data Index: 337474 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1143. Min Act: -0.1700

Data Index: 4029900 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1243. Min Act: -0.1700

Data Index: 6012480 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.0967. Min Act: -0.1700

Data Index: 7081155 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.0975. Min Act: -0.1700

Data Index: 2004845 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.1124. Min Act: -0.1700

Data Index: 3689143 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.0884. Min Act: -0.1700

Data Index: 716616 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.3162. Min Range: -3.3162

Max Act: 3.0806. Min Act: -0.1700

Data Index: 3824753 (Open Web Text)

Max Activating Token Index: 10