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

Dataset: Open Web Text

Neuron 1394 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: 3.0678. Min Range: -3.0678

Max Act: 3.0678. Min Act: -0.1700

Data Index: 7203679 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 3.0678. Min Range: -3.0678

Max Act: 3.0296. Min Act: -0.1700

Data Index: 6294842 (Open Web Text)

Max Activating Token Index: 362

Text #2

Max Range: 3.0678. Min Range: -3.0678

Max Act: 3.0294. Min Act: -0.1700

Data Index: 306906 (Open Web Text)

Max Activating Token Index: 495

Text #3

Max Range: 3.0678. Min Range: -3.0678

Max Act: 3.0128. Min Act: -0.1700

Data Index: 4349331 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.9627. Min Act: -0.1700

Data Index: 2180207 (Open Web Text)

Max Activating Token Index: 855

Text #5

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.9283. Min Act: -0.1700

Data Index: 8795214 (Open Web Text)

Max Activating Token Index: 246

Text #6

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.9482. Min Act: -0.1700

Data Index: 1109854 (Open Web Text)

Max Activating Token Index: 295

Text #7

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.9171. Min Act: -0.1700

Data Index: 8515803 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.9193. Min Act: -0.1700

Data Index: 6156882 (Open Web Text)

Max Activating Token Index: 820

Text #9

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.9535. Min Act: -0.1700

Data Index: 5965946 (Open Web Text)

Max Activating Token Index: 491

Text #10

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.9146. Min Act: -0.1700

Data Index: 8225751 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.9181. Min Act: -0.1700

Data Index: 3484498 (Open Web Text)

Max Activating Token Index: 346

Text #12

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.8971. Min Act: -0.1700

Data Index: 2579387 (Open Web Text)

Max Activating Token Index: 966

Text #13

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.8993. Min Act: -0.1700

Data Index: 3628111 (Open Web Text)

Max Activating Token Index: 133

Text #14

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.8875. Min Act: -0.1700

Data Index: 2025358 (Open Web Text)

Max Activating Token Index: 40

Text #15

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.8956. Min Act: -0.1700

Data Index: 7126485 (Open Web Text)

Max Activating Token Index: 613

Text #16

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.8859. Min Act: -0.1700

Data Index: 4735805 (Open Web Text)

Max Activating Token Index: 40

Text #17

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.8910. Min Act: -0.1700

Data Index: 274993 (Open Web Text)

Max Activating Token Index: 192

Text #18

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.8875. Min Act: -0.1700

Data Index: 7022314 (Open Web Text)

Max Activating Token Index: 878

Text #19

Max Range: 3.0678. Min Range: -3.0678

Max Act: 2.8740. Min Act: -0.1700

Data Index: 3318169 (Open Web Text)

Max Activating Token Index: 508