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

Dataset: Open Web Text

Neuron 1109 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: 3.0806. Min Range: -3.0806

Max Act: 3.0806. Min Act: -0.1700

Data Index: 8802103 (Open Web Text)

Max Activating Token Index: 408

Text #1

Max Range: 3.0806. Min Range: -3.0806

Max Act: 3.0234. Min Act: -0.1700

Data Index: 7553949 (Open Web Text)

Max Activating Token Index: 261

Text #2

Max Range: 3.0806. Min Range: -3.0806

Max Act: 3.0132. Min Act: -0.1700

Data Index: 7144628 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9848. Min Act: -0.1700

Data Index: 7855682 (Open Web Text)

Max Activating Token Index: 691

Text #4

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9685. Min Act: -0.1700

Data Index: 3182490 (Open Web Text)

Max Activating Token Index: 43

Text #5

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9689. Min Act: -0.1700

Data Index: 1781131 (Open Web Text)

Max Activating Token Index: 216

Text #6

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9746. Min Act: -0.1700

Data Index: 8630485 (Open Web Text)

Max Activating Token Index: 642

Text #7

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9550. Min Act: -0.1700

Data Index: 6630430 (Open Web Text)

Max Activating Token Index: 777

Text #8

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9579. Min Act: -0.1700

Data Index: 4623379 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9447. Min Act: -0.1700

Data Index: 6768767 (Open Web Text)

Max Activating Token Index: 247

Text #10

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9088. Min Act: -0.1700

Data Index: 7835146 (Open Web Text)

Max Activating Token Index: 626

Text #11

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9201. Min Act: -0.1700

Data Index: 8330167 (Open Web Text)

Max Activating Token Index: 126

Text #12

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9051. Min Act: -0.1700

Data Index: 559294 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.9017. Min Act: -0.1700

Data Index: 86839 (Open Web Text)

Max Activating Token Index: 578

Text #14

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.8934. Min Act: -0.1700

Data Index: 3739650 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.8840. Min Act: -0.1700

Data Index: 2491258 (Open Web Text)

Max Activating Token Index: 128

Text #16

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.8810. Min Act: -0.1700

Data Index: 5510081 (Open Web Text)

Max Activating Token Index: 473

Text #17

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.8661. Min Act: -0.1700

Data Index: 4382954 (Open Web Text)

Max Activating Token Index: 37

Text #18

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.8697. Min Act: -0.1700

Data Index: 6579411 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.8607. Min Act: -0.1700

Data Index: 173996 (Open Web Text)

Max Activating Token Index: 107