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

Dataset: Open Web Text

Neuron 587 in Layer 4

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: 2.0101. Min Range: -2.0101

Max Act: 2.0101. Min Act: -0.1700

Data Index: 4131493 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.9956. Min Act: -0.1700

Data Index: 4006002 (Open Web Text)

Max Activating Token Index: 985

Text #2

Max Range: 2.0101. Min Range: -2.0101

Max Act: 2.0011. Min Act: -0.1700

Data Index: 6248366 (Open Web Text)

Max Activating Token Index: 467

Text #3

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.9750. Min Act: -0.1700

Data Index: 8369471 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.9492. Min Act: -0.1700

Data Index: 863715 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.9507. Min Act: -0.1700

Data Index: 7908365 (Open Web Text)

Max Activating Token Index: 257

Text #6

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8831. Min Act: -0.1700

Data Index: 4025948 (Open Web Text)

Max Activating Token Index: 529

Text #7

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8704. Min Act: -0.1700

Data Index: 5261416 (Open Web Text)

Max Activating Token Index: 902

Text #8

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.9065. Min Act: -0.1700

Data Index: 5791392 (Open Web Text)

Max Activating Token Index: 642

Text #9

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8567. Min Act: -0.1700

Data Index: 2693855 (Open Web Text)

Max Activating Token Index: 557

Text #10

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8865. Min Act: -0.1700

Data Index: 7908369 (Open Web Text)

Max Activating Token Index: 684

Text #11

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8340. Min Act: -0.1700

Data Index: 794408 (Open Web Text)

Max Activating Token Index: 505

Text #12

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8739. Min Act: -0.1700

Data Index: 7908360 (Open Web Text)

Max Activating Token Index: 162

Text #13

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8452. Min Act: -0.1700

Data Index: 2588678 (Open Web Text)

Max Activating Token Index: 88

Text #14

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8600. Min Act: -0.1700

Data Index: 1921071 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8306. Min Act: -0.1700

Data Index: 2287865 (Open Web Text)

Max Activating Token Index: 580

Text #16

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8397. Min Act: -0.1700

Data Index: 2990741 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8187. Min Act: -0.1700

Data Index: 2588512 (Open Web Text)

Max Activating Token Index: 365

Text #18

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8229. Min Act: -0.1700

Data Index: 1206441 (Open Web Text)

Max Activating Token Index: 563

Text #19

Max Range: 2.0101. Min Range: -2.0101

Max Act: 1.8136. Min Act: -0.1700

Data Index: 1432327 (Open Web Text)

Max Activating Token Index: 163