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

Dataset: Open Web Text

Neuron 212 in Layer 6

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: 4.1159. Min Range: -4.1159

Max Act: 4.1159. Min Act: -0.1700

Data Index: 6978370 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 4.1159. Min Range: -4.1159

Max Act: 4.0487. Min Act: -0.1700

Data Index: 2027418 (Open Web Text)

Max Activating Token Index: 687

Text #2

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9987. Min Act: -0.1700

Data Index: 4133943 (Open Web Text)

Max Activating Token Index: 641

Text #3

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9684. Min Act: -0.1700

Data Index: 1514940 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9596. Min Act: -0.1700

Data Index: 7116756 (Open Web Text)

Max Activating Token Index: 131

Text #5

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9457. Min Act: -0.1700

Data Index: 4238354 (Open Web Text)

Max Activating Token Index: 724

Text #6

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9146. Min Act: -0.1700

Data Index: 6532958 (Open Web Text)

Max Activating Token Index: 59

Text #7

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9169. Min Act: -0.1700

Data Index: 7803930 (Open Web Text)

Max Activating Token Index: 278

Text #8

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9011. Min Act: -0.1700

Data Index: 4573563 (Open Web Text)

Max Activating Token Index: 594

Text #9

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8786. Min Act: -0.1700

Data Index: 8425698 (Open Web Text)

Max Activating Token Index: 227

Text #10

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8652. Min Act: -0.1700

Data Index: 441635 (Open Web Text)

Max Activating Token Index: 740

Text #11

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8713. Min Act: -0.1700

Data Index: 3795696 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8434. Min Act: -0.1700

Data Index: 230814 (Open Web Text)

Max Activating Token Index: 155

Text #13

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8629. Min Act: -0.1700

Data Index: 4373720 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8678. Min Act: -0.1700

Data Index: 2613875 (Open Web Text)

Max Activating Token Index: 768

Text #15

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8421. Min Act: -0.1700

Data Index: 7334689 (Open Web Text)

Max Activating Token Index: 173

Text #16

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8440. Min Act: -0.1700

Data Index: 6757903 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8483. Min Act: -0.1700

Data Index: 5507798 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8495. Min Act: -0.1700

Data Index: 4814166 (Open Web Text)

Max Activating Token Index: 343

Text #19

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8189. Min Act: -0.1700

Data Index: 802518 (Open Web Text)

Max Activating Token Index: 587