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

Dataset: Open Web Text

Neuron 2749 in Layer 2

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: 4.9604. Min Range: -4.9604

Max Act: 4.9604. Min Act: -0.1700

Data Index: 4613586 (Open Web Text)

Max Activating Token Index: 97

Text #1

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.9188. Min Act: -0.1700

Data Index: 3323952 (Open Web Text)

Max Activating Token Index: 172

Text #2

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.8592. Min Act: -0.1700

Data Index: 6144532 (Open Web Text)

Max Activating Token Index: 196

Text #3

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.8641. Min Act: -0.1700

Data Index: 2971203 (Open Web Text)

Max Activating Token Index: 153

Text #4

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.8381. Min Act: -0.1700

Data Index: 8202685 (Open Web Text)

Max Activating Token Index: 319

Text #5

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.8303. Min Act: -0.1700

Data Index: 6308191 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7714. Min Act: -0.1700

Data Index: 2636093 (Open Web Text)

Max Activating Token Index: 435

Text #7

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7886. Min Act: -0.1700

Data Index: 481390 (Open Web Text)

Max Activating Token Index: 79

Text #8

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7801. Min Act: -0.1700

Data Index: 2192537 (Open Web Text)

Max Activating Token Index: 50

Text #9

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7665. Min Act: -0.1700

Data Index: 7241090 (Open Web Text)

Max Activating Token Index: 985

Text #10

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7263. Min Act: -0.1700

Data Index: 5326912 (Open Web Text)

Max Activating Token Index: 677

Text #11

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7300. Min Act: -0.1700

Data Index: 2035181 (Open Web Text)

Max Activating Token Index: 135

Text #12

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7347. Min Act: -0.1700

Data Index: 4529840 (Open Web Text)

Max Activating Token Index: 93

Text #13

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7387. Min Act: -0.1700

Data Index: 6387086 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7399. Min Act: -0.1700

Data Index: 5346484 (Open Web Text)

Max Activating Token Index: 58

Text #15

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7237. Min Act: -0.1700

Data Index: 5125094 (Open Web Text)

Max Activating Token Index: 53

Text #16

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7152. Min Act: -0.1700

Data Index: 511602 (Open Web Text)

Max Activating Token Index: 774

Text #17

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7228. Min Act: -0.1700

Data Index: 5569106 (Open Web Text)

Max Activating Token Index: 220

Text #18

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.6822. Min Act: -0.1700

Data Index: 2895339 (Open Web Text)

Max Activating Token Index: 61

Text #19

Max Range: 4.9604. Min Range: -4.9604

Max Act: 4.7119. Min Act: -0.1700

Data Index: 10243 (Open Web Text)

Max Activating Token Index: 568