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

Dataset: Open Web Text

Neuron 2003 in Layer 5

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: 4.4952. Min Range: -4.4952

Max Act: 4.4952. Min Act: -0.1700

Data Index: 3787986 (Open Web Text)

Max Activating Token Index: 146

Text #1

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.4575. Min Act: -0.1700

Data Index: 6099918 (Open Web Text)

Max Activating Token Index: 452

Text #2

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.4593. Min Act: -0.1700

Data Index: 2774628 (Open Web Text)

Max Activating Token Index: 502

Text #3

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.4452. Min Act: -0.1700

Data Index: 2296700 (Open Web Text)

Max Activating Token Index: 257

Text #4

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.4331. Min Act: -0.1700

Data Index: 5517967 (Open Web Text)

Max Activating Token Index: 79

Text #5

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.4001. Min Act: -0.1700

Data Index: 7503507 (Open Web Text)

Max Activating Token Index: 384

Text #6

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3968. Min Act: -0.1700

Data Index: 4864352 (Open Web Text)

Max Activating Token Index: 99

Text #7

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3866. Min Act: -0.1700

Data Index: 1606631 (Open Web Text)

Max Activating Token Index: 351

Text #8

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3979. Min Act: -0.1700

Data Index: 175739 (Open Web Text)

Max Activating Token Index: 60

Text #9

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3468. Min Act: -0.1700

Data Index: 1413486 (Open Web Text)

Max Activating Token Index: 224

Text #10

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3655. Min Act: -0.1700

Data Index: 7377478 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3814. Min Act: -0.1700

Data Index: 1606644 (Open Web Text)

Max Activating Token Index: 883

Text #12

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3789. Min Act: -0.1700

Data Index: 2238507 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3833. Min Act: -0.1700

Data Index: 2296689 (Open Web Text)

Max Activating Token Index: 116

Text #14

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3721. Min Act: -0.1700

Data Index: 1356910 (Open Web Text)

Max Activating Token Index: 77

Text #15

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3643. Min Act: -0.1700

Data Index: 5945070 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3588. Min Act: -0.1700

Data Index: 5945073 (Open Web Text)

Max Activating Token Index: 439

Text #17

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3261. Min Act: -0.1700

Data Index: 8114283 (Open Web Text)

Max Activating Token Index: 815

Text #18

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3348. Min Act: -0.1700

Data Index: 5801526 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3153. Min Act: -0.1700

Data Index: 6360716 (Open Web Text)

Max Activating Token Index: 636