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

Dataset: Open Web Text

Neuron 370 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: 5.2126. Min Range: -5.2126

Max Act: 5.2126. Min Act: -0.1700

Data Index: 6979139 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9994. Min Act: -0.1700

Data Index: 3847324 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.2126. Min Range: -5.2126

Max Act: 5.0071. Min Act: -0.1700

Data Index: 3772458 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 5.2126. Min Range: -5.2126

Max Act: 5.0159. Min Act: -0.1700

Data Index: 6738564 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9831. Min Act: -0.1700

Data Index: 452152 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9632. Min Act: -0.1700

Data Index: 5895537 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9901. Min Act: -0.1700

Data Index: 7600409 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9582. Min Act: -0.1700

Data Index: 8399013 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9449. Min Act: -0.1700

Data Index: 7500839 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9146. Min Act: -0.1700

Data Index: 1232059 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9241. Min Act: -0.1700

Data Index: 8532090 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9165. Min Act: -0.1700

Data Index: 7235595 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.8999. Min Act: -0.1700

Data Index: 3220709 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9362. Min Act: -0.1700

Data Index: 665106 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9155. Min Act: -0.1700

Data Index: 3134005 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9142. Min Act: -0.1700

Data Index: 2955108 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9151. Min Act: -0.1700

Data Index: 6229977 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9194. Min Act: -0.1700

Data Index: 5517460 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9101. Min Act: -0.1700

Data Index: 4798327 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.8700. Min Act: -0.1700

Data Index: 3727028 (Open Web Text)

Max Activating Token Index: 9