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

Dataset: Open Web Text

Neuron 1216 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: 3.0746. Min Range: -3.0746

Max Act: 3.0746. Min Act: -0.1700

Data Index: 8378077 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9037. Min Act: -0.1700

Data Index: 2099801 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9086. Min Act: -0.1700

Data Index: 3144048 (Open Web Text)

Max Activating Token Index: 223

Text #3

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9145. Min Act: -0.1700

Data Index: 5105069 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9064. Min Act: -0.1700

Data Index: 1374748 (Open Web Text)

Max Activating Token Index: 170

Text #5

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9138. Min Act: -0.1700

Data Index: 520252 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9018. Min Act: -0.1700

Data Index: 5755390 (Open Web Text)

Max Activating Token Index: 118

Text #7

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9036. Min Act: -0.1700

Data Index: 3113577 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.8980. Min Act: -0.1700

Data Index: 5492486 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9023. Min Act: -0.1700

Data Index: 6414943 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.8980. Min Act: -0.1700

Data Index: 957365 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.8980. Min Act: -0.1700

Data Index: 2194294 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.8980. Min Act: -0.1700

Data Index: 1002769 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.8939. Min Act: -0.1700

Data Index: 5496968 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9077. Min Act: -0.1700

Data Index: 4285444 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.8980. Min Act: -0.1700

Data Index: 5264044 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9030. Min Act: -0.1700

Data Index: 597048 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.8980. Min Act: -0.1700

Data Index: 3158951 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9029. Min Act: -0.1700

Data Index: 4632387 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.8980. Min Act: -0.1700

Data Index: 7438103 (Open Web Text)

Max Activating Token Index: 2