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

Dataset: Open Web Text

Neuron 662 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: 1.4651. Min Range: -1.4651

Max Act: 1.4651. Min Act: -0.1700

Data Index: 4009734 (Open Web Text)

Max Activating Token Index: 47

Text #1

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4447. Min Act: -0.1700

Data Index: 4476654 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4315. Min Act: -0.1700

Data Index: 717558 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4328. Min Act: -0.1700

Data Index: 8079614 (Open Web Text)

Max Activating Token Index: 340

Text #4

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4228. Min Act: -0.1700

Data Index: 2626081 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4097. Min Act: -0.1700

Data Index: 149204 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4223. Min Act: -0.1700

Data Index: 4428699 (Open Web Text)

Max Activating Token Index: 119

Text #7

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4183. Min Act: -0.1700

Data Index: 4113229 (Open Web Text)

Max Activating Token Index: 616

Text #8

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3978. Min Act: -0.1700

Data Index: 8334573 (Open Web Text)

Max Activating Token Index: 113

Text #9

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4064. Min Act: -0.1700

Data Index: 8563756 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3863. Min Act: -0.1700

Data Index: 3484581 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3927. Min Act: -0.1700

Data Index: 6390497 (Open Web Text)

Max Activating Token Index: 651

Text #12

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3841. Min Act: -0.1700

Data Index: 690550 (Open Web Text)

Max Activating Token Index: 29

Text #13

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3817. Min Act: -0.1700

Data Index: 2723633 (Open Web Text)

Max Activating Token Index: 746

Text #14

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3900. Min Act: -0.1700

Data Index: 6929915 (Open Web Text)

Max Activating Token Index: 478

Text #15

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3883. Min Act: -0.1700

Data Index: 2493856 (Open Web Text)

Max Activating Token Index: 131

Text #16

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3757. Min Act: -0.1700

Data Index: 7386818 (Open Web Text)

Max Activating Token Index: 180

Text #17

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3741. Min Act: -0.1699

Data Index: 6003733 (Open Web Text)

Max Activating Token Index: 87

Text #18

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3756. Min Act: -0.1700

Data Index: 479351 (Open Web Text)

Max Activating Token Index: 1002

Text #19

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3789. Min Act: -0.1700

Data Index: 4804503 (Open Web Text)

Max Activating Token Index: 233