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

Dataset: Open Web Text

Neuron 59 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: 3.3687. Min Range: -3.3687

Max Act: 3.3687. Min Act: -0.1700

Data Index: 2769604 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.3687. Min Act: -0.1700

Data Index: 4454374 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.3687. Min Act: -0.1700

Data Index: 8654257 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.3687. Min Act: -0.1700

Data Index: 7269114 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.3687. Min Act: -0.1700

Data Index: 29872 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.3605. Min Act: -0.1700

Data Index: 263329 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.3262. Min Act: -0.1700

Data Index: 8709099 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2789. Min Act: -0.1700

Data Index: 1955703 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2681. Min Act: -0.1700

Data Index: 4096574 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2483. Min Act: -0.1700

Data Index: 368122 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2483. Min Act: -0.1700

Data Index: 1928967 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2390. Min Act: -0.1700

Data Index: 5220753 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2483. Min Act: -0.1700

Data Index: 6326440 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2407. Min Act: -0.1700

Data Index: 4909687 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2412. Min Act: -0.1700

Data Index: 5789273 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2055. Min Act: -0.1700

Data Index: 7345339 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2291. Min Act: -0.1700

Data Index: 8822787 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2064. Min Act: -0.1700

Data Index: 542086 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1939. Min Act: -0.1700

Data Index: 691181 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1965. Min Act: -0.1700

Data Index: 2657067 (Open Web Text)

Max Activating Token Index: 3