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

Dataset: Open Web Text

Neuron 1515 in Layer 1

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: 2.1095. Min Range: -2.1095

Max Act: 2.1095. Min Act: -0.1700

Data Index: 5915294 (Open Web Text)

Max Activating Token Index: 615

Text #1

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9952. Min Act: -0.1700

Data Index: 5915293 (Open Web Text)

Max Activating Token Index: 613

Text #2

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9956. Min Act: -0.1700

Data Index: 6590838 (Open Web Text)

Max Activating Token Index: 254

Text #3

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9869. Min Act: -0.1700

Data Index: 107833 (Open Web Text)

Max Activating Token Index: 528

Text #4

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9723. Min Act: -0.1700

Data Index: 6380861 (Open Web Text)

Max Activating Token Index: 328

Text #5

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9567. Min Act: -0.1700

Data Index: 7452098 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9437. Min Act: -0.1700

Data Index: 5746406 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9597. Min Act: -0.1700

Data Index: 4611667 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9202. Min Act: -0.1700

Data Index: 1558510 (Open Web Text)

Max Activating Token Index: 66

Text #9

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9418. Min Act: -0.1700

Data Index: 8723878 (Open Web Text)

Max Activating Token Index: 743

Text #10

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9031. Min Act: -0.1700

Data Index: 5684577 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9043. Min Act: -0.1700

Data Index: 6324803 (Open Web Text)

Max Activating Token Index: 862

Text #12

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9035. Min Act: -0.1699

Data Index: 2651986 (Open Web Text)

Max Activating Token Index: 119

Text #13

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.8920. Min Act: -0.1700

Data Index: 3875273 (Open Web Text)

Max Activating Token Index: 807

Text #14

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.8893. Min Act: -0.1700

Data Index: 6949200 (Open Web Text)

Max Activating Token Index: 56

Text #15

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.8974. Min Act: -0.1700

Data Index: 4793153 (Open Web Text)

Max Activating Token Index: 644

Text #16

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9042. Min Act: -0.1700

Data Index: 6140618 (Open Web Text)

Max Activating Token Index: 418

Text #17

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.8869. Min Act: -0.1700

Data Index: 4740374 (Open Web Text)

Max Activating Token Index: 143

Text #18

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.8772. Min Act: -0.1700

Data Index: 3926328 (Open Web Text)

Max Activating Token Index: 829

Text #19

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.8822. Min Act: -0.1700

Data Index: 159949 (Open Web Text)

Max Activating Token Index: 616