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

Dataset: Open Web Text

Neuron 2343 in Layer 5

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: 5.6523. Min Range: -5.6523

Max Act: 5.6523. Min Act: -0.1700

Data Index: 6805610 (Open Web Text)

Max Activating Token Index: 334

Text #1

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.5983. Min Act: -0.1700

Data Index: 2500443 (Open Web Text)

Max Activating Token Index: 104

Text #2

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.5927. Min Act: -0.1700

Data Index: 6316800 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.5555. Min Act: -0.1700

Data Index: 4758878 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.5116. Min Act: -0.1700

Data Index: 1850633 (Open Web Text)

Max Activating Token Index: 250

Text #5

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.4832. Min Act: -0.1700

Data Index: 2570309 (Open Web Text)

Max Activating Token Index: 105

Text #6

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.4700. Min Act: -0.1700

Data Index: 4227853 (Open Web Text)

Max Activating Token Index: 177

Text #7

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.4363. Min Act: -0.1700

Data Index: 2540354 (Open Web Text)

Max Activating Token Index: 185

Text #8

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.3972. Min Act: -0.1700

Data Index: 5669800 (Open Web Text)

Max Activating Token Index: 275

Text #9

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.4071. Min Act: -0.1700

Data Index: 6507503 (Open Web Text)

Max Activating Token Index: 110

Text #10

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.4085. Min Act: -0.1700

Data Index: 4411654 (Open Web Text)

Max Activating Token Index: 515

Text #11

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.4297. Min Act: -0.1700

Data Index: 7880855 (Open Web Text)

Max Activating Token Index: 640

Text #12

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.3957. Min Act: -0.1700

Data Index: 5416457 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.3291. Min Act: -0.1700

Data Index: 647015 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.3603. Min Act: -0.1700

Data Index: 2863951 (Open Web Text)

Max Activating Token Index: 701

Text #15

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.3643. Min Act: -0.1700

Data Index: 3191434 (Open Web Text)

Max Activating Token Index: 332

Text #16

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.2949. Min Act: -0.1700

Data Index: 5714972 (Open Web Text)

Max Activating Token Index: 730

Text #17

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.2991. Min Act: -0.1700

Data Index: 2895999 (Open Web Text)

Max Activating Token Index: 361

Text #18

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.2782. Min Act: -0.1700

Data Index: 50019 (Open Web Text)

Max Activating Token Index: 168

Text #19

Max Range: 5.6523. Min Range: -5.6523

Max Act: 5.2835. Min Act: -0.1700

Data Index: 4134065 (Open Web Text)

Max Activating Token Index: 162