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

Dataset: Open Web Text

Neuron 1094 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: 4.7107. Min Range: -4.7107

Max Act: 4.7107. Min Act: -0.1700

Data Index: 1241465 (Open Web Text)

Max Activating Token Index: 959

Text #1

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.6713. Min Act: -0.1700

Data Index: 7903673 (Open Web Text)

Max Activating Token Index: 73

Text #2

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5980. Min Act: -0.1700

Data Index: 5303652 (Open Web Text)

Max Activating Token Index: 560

Text #3

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.6140. Min Act: -0.1700

Data Index: 1910820 (Open Web Text)

Max Activating Token Index: 351

Text #4

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5953. Min Act: -0.1700

Data Index: 7367081 (Open Web Text)

Max Activating Token Index: 423

Text #5

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5785. Min Act: -0.1700

Data Index: 3841506 (Open Web Text)

Max Activating Token Index: 154

Text #6

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5690. Min Act: -0.1700

Data Index: 1402746 (Open Web Text)

Max Activating Token Index: 559

Text #7

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5904. Min Act: -0.1700

Data Index: 7464527 (Open Web Text)

Max Activating Token Index: 60

Text #8

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5791. Min Act: -0.1700

Data Index: 8578855 (Open Web Text)

Max Activating Token Index: 285

Text #9

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5918. Min Act: -0.1700

Data Index: 3589141 (Open Web Text)

Max Activating Token Index: 226

Text #10

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5402. Min Act: -0.1700

Data Index: 2384737 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5519. Min Act: -0.1700

Data Index: 8642081 (Open Web Text)

Max Activating Token Index: 442

Text #12

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5703. Min Act: -0.1700

Data Index: 688505 (Open Web Text)

Max Activating Token Index: 960

Text #13

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5350. Min Act: -0.1700

Data Index: 5391027 (Open Web Text)

Max Activating Token Index: 247

Text #14

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5144. Min Act: -0.1700

Data Index: 8290627 (Open Web Text)

Max Activating Token Index: 196

Text #15

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5367. Min Act: -0.1700

Data Index: 1282804 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5025. Min Act: -0.1700

Data Index: 6307031 (Open Web Text)

Max Activating Token Index: 56

Text #17

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5441. Min Act: -0.1700

Data Index: 8316101 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.5198. Min Act: -0.1700

Data Index: 5154373 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 4.7107. Min Range: -4.7107

Max Act: 4.4983. Min Act: -0.1700

Data Index: 855707 (Open Web Text)

Max Activating Token Index: 34