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

Dataset: Open Web Text

Neuron 591 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: 3.1134. Min Range: -3.1134

Max Act: 3.1134. Min Act: -0.1700

Data Index: 814357 (Open Web Text)

Max Activating Token Index: 1003

Text #1

Max Range: 3.1134. Min Range: -3.1134

Max Act: 3.0948. Min Act: -0.1700

Data Index: 814358 (Open Web Text)

Max Activating Token Index: 180

Text #2

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.9405. Min Act: -0.1700

Data Index: 6030029 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.9481. Min Act: -0.1700

Data Index: 5188418 (Open Web Text)

Max Activating Token Index: 383

Text #4

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.9361. Min Act: -0.1700

Data Index: 147555 (Open Web Text)

Max Activating Token Index: 819

Text #5

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.9321. Min Act: -0.1700

Data Index: 7044761 (Open Web Text)

Max Activating Token Index: 347

Text #6

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.9157. Min Act: -0.1700

Data Index: 4997164 (Open Web Text)

Max Activating Token Index: 669

Text #7

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8906. Min Act: -0.1700

Data Index: 2035998 (Open Web Text)

Max Activating Token Index: 161

Text #8

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8738. Min Act: -0.1700

Data Index: 2822616 (Open Web Text)

Max Activating Token Index: 147

Text #9

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8899. Min Act: -0.1700

Data Index: 5949054 (Open Web Text)

Max Activating Token Index: 318

Text #10

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8716. Min Act: -0.1700

Data Index: 4406408 (Open Web Text)

Max Activating Token Index: 221

Text #11

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8768. Min Act: -0.1700

Data Index: 3960280 (Open Web Text)

Max Activating Token Index: 538

Text #12

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8613. Min Act: -0.1700

Data Index: 7741554 (Open Web Text)

Max Activating Token Index: 894

Text #13

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8383. Min Act: -0.1700

Data Index: 6505274 (Open Web Text)

Max Activating Token Index: 97

Text #14

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8289. Min Act: -0.1700

Data Index: 8763958 (Open Web Text)

Max Activating Token Index: 113

Text #15

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8394. Min Act: -0.1700

Data Index: 7958885 (Open Web Text)

Max Activating Token Index: 153

Text #16

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8184. Min Act: -0.1700

Data Index: 5308243 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8143. Min Act: -0.1700

Data Index: 3679844 (Open Web Text)

Max Activating Token Index: 749

Text #18

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8159. Min Act: -0.1700

Data Index: 1142941 (Open Web Text)

Max Activating Token Index: 765

Text #19

Max Range: 3.1134. Min Range: -3.1134

Max Act: 2.8318. Min Act: -0.1700

Data Index: 3610300 (Open Web Text)

Max Activating Token Index: 469