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

Dataset: Open Web Text

Neuron 1037 in Layer 0

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: 6.6186. Min Range: -6.6186

Max Act: 6.6186. Min Act: -0.1700

Data Index: 3903701 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.5875. Min Act: -0.1700

Data Index: 4296802 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.5819. Min Act: -0.1700

Data Index: 7381003 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.5789. Min Act: -0.1700

Data Index: 7099884 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.5130. Min Act: -0.1700

Data Index: 7703253 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.5277. Min Act: -0.1700

Data Index: 1376182 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.5274. Min Act: -0.1700

Data Index: 7912033 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.4662. Min Act: -0.1700

Data Index: 3230953 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.4765. Min Act: -0.1700

Data Index: 79567 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.4616. Min Act: -0.1700

Data Index: 7447070 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.4828. Min Act: -0.1700

Data Index: 4036531 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.4474. Min Act: -0.1700

Data Index: 6684845 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.4351. Min Act: -0.1700

Data Index: 756217 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.4334. Min Act: -0.1700

Data Index: 2170169 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.4587. Min Act: -0.1700

Data Index: 133070 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.4292. Min Act: -0.1700

Data Index: 2416776 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.4062. Min Act: -0.1700

Data Index: 632583 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.3851. Min Act: -0.1700

Data Index: 174412 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.3672. Min Act: -0.1700

Data Index: 3928232 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 6.6186. Min Range: -6.6186

Max Act: 6.3837. Min Act: -0.1700

Data Index: 7626000 (Open Web Text)

Max Activating Token Index: 5