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

Dataset: Open Web Text

Neuron 2209 in Layer 3

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: 3.8789. Min Range: -3.8789

Max Act: 3.8789. Min Act: -0.1700

Data Index: 6785383 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7801. Min Act: -0.1700

Data Index: 4276061 (Open Web Text)

Max Activating Token Index: 539

Text #2

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7964. Min Act: -0.1700

Data Index: 632329 (Open Web Text)

Max Activating Token Index: 627

Text #3

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7536. Min Act: -0.1700

Data Index: 6737824 (Open Web Text)

Max Activating Token Index: 563

Text #4

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7173. Min Act: -0.1700

Data Index: 4630582 (Open Web Text)

Max Activating Token Index: 379

Text #5

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7486. Min Act: -0.1700

Data Index: 1231301 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7129. Min Act: -0.1700

Data Index: 2172242 (Open Web Text)

Max Activating Token Index: 109

Text #7

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7312. Min Act: -0.1700

Data Index: 4172675 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7072. Min Act: -0.1700

Data Index: 8491269 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7227. Min Act: -0.1700

Data Index: 2454761 (Open Web Text)

Max Activating Token Index: 965

Text #10

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6982. Min Act: -0.1700

Data Index: 6339579 (Open Web Text)

Max Activating Token Index: 557

Text #11

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6682. Min Act: -0.1700

Data Index: 3976112 (Open Web Text)

Max Activating Token Index: 980

Text #12

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6742. Min Act: -0.1700

Data Index: 7184012 (Open Web Text)

Max Activating Token Index: 779

Text #13

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6905. Min Act: -0.1700

Data Index: 7622860 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6915. Min Act: -0.1700

Data Index: 2246352 (Open Web Text)

Max Activating Token Index: 91

Text #15

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6470. Min Act: -0.1700

Data Index: 2290936 (Open Web Text)

Max Activating Token Index: 220

Text #16

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6700. Min Act: -0.1700

Data Index: 2080015 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6730. Min Act: -0.1700

Data Index: 3908476 (Open Web Text)

Max Activating Token Index: 103

Text #18

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6461. Min Act: -0.1700

Data Index: 616731 (Open Web Text)

Max Activating Token Index: 578

Text #19

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6533. Min Act: -0.1700

Data Index: 4656304 (Open Web Text)

Max Activating Token Index: 901