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

Dataset: Open Web Text

Neuron 1680 in Layer 6

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: 4.0970. Min Range: -4.0970

Max Act: 4.0970. Min Act: -0.1700

Data Index: 559773 (Open Web Text)

Max Activating Token Index: 762

Text #1

Max Range: 4.0970. Min Range: -4.0970

Max Act: 4.0961. Min Act: -0.1700

Data Index: 6314371 (Open Web Text)

Max Activating Token Index: 97

Text #2

Max Range: 4.0970. Min Range: -4.0970

Max Act: 4.0970. Min Act: -0.1700

Data Index: 3497547 (Open Web Text)

Max Activating Token Index: 798

Text #3

Max Range: 4.0970. Min Range: -4.0970

Max Act: 4.0892. Min Act: -0.1700

Data Index: 2179760 (Open Web Text)

Max Activating Token Index: 540

Text #4

Max Range: 4.0970. Min Range: -4.0970

Max Act: 4.0559. Min Act: -0.1700

Data Index: 5734240 (Open Web Text)

Max Activating Token Index: 733

Text #5

Max Range: 4.0970. Min Range: -4.0970

Max Act: 4.0418. Min Act: -0.1700

Data Index: 7289468 (Open Web Text)

Max Activating Token Index: 727

Text #6

Max Range: 4.0970. Min Range: -4.0970

Max Act: 4.0077. Min Act: -0.1700

Data Index: 5128300 (Open Web Text)

Max Activating Token Index: 121

Text #7

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.9592. Min Act: -0.1700

Data Index: 3761400 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.9590. Min Act: -0.1700

Data Index: 8704633 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.9822. Min Act: -0.1700

Data Index: 6790938 (Open Web Text)

Max Activating Token Index: 196

Text #10

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.9497. Min Act: -0.1700

Data Index: 2750043 (Open Web Text)

Max Activating Token Index: 619

Text #11

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.9238. Min Act: -0.1700

Data Index: 1237624 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.8817. Min Act: -0.1700

Data Index: 5095814 (Open Web Text)

Max Activating Token Index: 404

Text #13

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.8685. Min Act: -0.1700

Data Index: 2210030 (Open Web Text)

Max Activating Token Index: 822

Text #14

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.8819. Min Act: -0.1700

Data Index: 137001 (Open Web Text)

Max Activating Token Index: 568

Text #15

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.9003. Min Act: -0.1700

Data Index: 3398571 (Open Web Text)

Max Activating Token Index: 552

Text #16

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.9030. Min Act: -0.1700

Data Index: 7493376 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.9025. Min Act: -0.1700

Data Index: 3530095 (Open Web Text)

Max Activating Token Index: 261

Text #18

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.8996. Min Act: -0.1700

Data Index: 7304674 (Open Web Text)

Max Activating Token Index: 972

Text #19

Max Range: 4.0970. Min Range: -4.0970

Max Act: 3.8539. Min Act: -0.1700

Data Index: 2819541 (Open Web Text)

Max Activating Token Index: 300