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

Dataset: Open Web Text

Neuron 36 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: 3.8517. Min Range: -3.8517

Max Act: 3.8517. Min Act: -0.1700

Data Index: 4905835 (Open Web Text)

Max Activating Token Index: 1010

Text #1

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.8133. Min Act: -0.1700

Data Index: 2295939 (Open Web Text)

Max Activating Token Index: 486

Text #2

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.7935. Min Act: -0.1700

Data Index: 4515692 (Open Web Text)

Max Activating Token Index: 963

Text #3

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6936. Min Act: -0.1700

Data Index: 4236772 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.7025. Min Act: -0.1700

Data Index: 8656685 (Open Web Text)

Max Activating Token Index: 850

Text #5

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6918. Min Act: -0.1700

Data Index: 124488 (Open Web Text)

Max Activating Token Index: 751

Text #6

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6875. Min Act: -0.1700

Data Index: 4014095 (Open Web Text)

Max Activating Token Index: 625

Text #7

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6627. Min Act: -0.1700

Data Index: 2787536 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6949. Min Act: -0.1700

Data Index: 208992 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6903. Min Act: -0.1700

Data Index: 2616661 (Open Web Text)

Max Activating Token Index: 741

Text #10

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6713. Min Act: -0.1700

Data Index: 6680335 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6435. Min Act: -0.1700

Data Index: 5539238 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6469. Min Act: -0.1700

Data Index: 1618799 (Open Web Text)

Max Activating Token Index: 173

Text #13

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6769. Min Act: -0.1700

Data Index: 6095629 (Open Web Text)

Max Activating Token Index: 212

Text #14

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6528. Min Act: -0.1700

Data Index: 2895462 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6645. Min Act: -0.1700

Data Index: 3922315 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6524. Min Act: -0.1700

Data Index: 5889832 (Open Web Text)

Max Activating Token Index: 213

Text #17

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6607. Min Act: -0.1700

Data Index: 207200 (Open Web Text)

Max Activating Token Index: 241

Text #18

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6533. Min Act: -0.1700

Data Index: 3969411 (Open Web Text)

Max Activating Token Index: 881

Text #19

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6211. Min Act: -0.1700

Data Index: 3606661 (Open Web Text)

Max Activating Token Index: 923