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

Dataset: Open Web Text

Neuron 875 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: 1.6456. Min Range: -1.6456

Max Act: 1.6456. Min Act: -0.1700

Data Index: 4951072 (Open Web Text)

Max Activating Token Index: 722

Text #1

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.6091. Min Act: -0.1700

Data Index: 6211298 (Open Web Text)

Max Activating Token Index: 58

Text #2

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5918. Min Act: -0.1700

Data Index: 577344 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5824. Min Act: -0.1700

Data Index: 4513410 (Open Web Text)

Max Activating Token Index: 113

Text #4

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5860. Min Act: -0.1700

Data Index: 2297415 (Open Web Text)

Max Activating Token Index: 81

Text #5

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5734. Min Act: -0.1700

Data Index: 8263519 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5758. Min Act: -0.1700

Data Index: 2750315 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5735. Min Act: -0.1699

Data Index: 7987511 (Open Web Text)

Max Activating Token Index: 532

Text #8

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5757. Min Act: -0.1700

Data Index: 1699052 (Open Web Text)

Max Activating Token Index: 726

Text #9

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5705. Min Act: -0.1700

Data Index: 8631401 (Open Web Text)

Max Activating Token Index: 135

Text #10

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5708. Min Act: -0.1700

Data Index: 8507102 (Open Web Text)

Max Activating Token Index: 72

Text #11

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5757. Min Act: -0.1700

Data Index: 2787460 (Open Web Text)

Max Activating Token Index: 394

Text #12

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5718. Min Act: -0.1700

Data Index: 5199588 (Open Web Text)

Max Activating Token Index: 68

Text #13

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5607. Min Act: -0.1700

Data Index: 5307210 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5657. Min Act: -0.1700

Data Index: 859503 (Open Web Text)

Max Activating Token Index: 215

Text #15

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5680. Min Act: -0.1700

Data Index: 4837261 (Open Web Text)

Max Activating Token Index: 680

Text #16

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5537. Min Act: -0.1700

Data Index: 4540128 (Open Web Text)

Max Activating Token Index: 104

Text #17

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5702. Min Act: -0.1700

Data Index: 4440741 (Open Web Text)

Max Activating Token Index: 701

Text #18

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5590. Min Act: -0.1700

Data Index: 2793076 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 1.6456. Min Range: -1.6456

Max Act: 1.5555. Min Act: -0.1700

Data Index: 3742415 (Open Web Text)

Max Activating Token Index: 691