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

Dataset: Open Web Text

Neuron 1616 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: 4.7649. Min Range: -4.7649

Max Act: 4.7649. Min Act: -0.1700

Data Index: 6835098 (Open Web Text)

Max Activating Token Index: 426

Text #1

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.7167. Min Act: -0.1700

Data Index: 8248518 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.7178. Min Act: -0.1700

Data Index: 8248519 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6844. Min Act: -0.1700

Data Index: 4653119 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6964. Min Act: -0.1700

Data Index: 5208819 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6951. Min Act: -0.1700

Data Index: 4239738 (Open Web Text)

Max Activating Token Index: 37

Text #6

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6672. Min Act: -0.1700

Data Index: 1097278 (Open Web Text)

Max Activating Token Index: 145

Text #7

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6679. Min Act: -0.1700

Data Index: 1279128 (Open Web Text)

Max Activating Token Index: 438

Text #8

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6793. Min Act: -0.1700

Data Index: 3015280 (Open Web Text)

Max Activating Token Index: 272

Text #9

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6640. Min Act: -0.1700

Data Index: 1488561 (Open Web Text)

Max Activating Token Index: 435

Text #10

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6810. Min Act: -0.1700

Data Index: 3905833 (Open Web Text)

Max Activating Token Index: 44

Text #11

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6771. Min Act: -0.1700

Data Index: 3919107 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6387. Min Act: -0.1700

Data Index: 950883 (Open Web Text)

Max Activating Token Index: 946

Text #13

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6423. Min Act: -0.1700

Data Index: 4052698 (Open Web Text)

Max Activating Token Index: 129

Text #14

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6343. Min Act: -0.1700

Data Index: 692027 (Open Web Text)

Max Activating Token Index: 361

Text #15

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6334. Min Act: -0.1700

Data Index: 5208818 (Open Web Text)

Max Activating Token Index: 977

Text #16

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6501. Min Act: -0.1700

Data Index: 3437216 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6462. Min Act: -0.1700

Data Index: 888167 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6325. Min Act: -0.1700

Data Index: 4308733 (Open Web Text)

Max Activating Token Index: 405

Text #19

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.6223. Min Act: -0.1700

Data Index: 888165 (Open Web Text)

Max Activating Token Index: 385