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

Dataset: Open Web Text

Neuron 657 in Layer 1

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: 3.5343. Min Range: -3.5343

Max Act: 3.5343. Min Act: -0.1700

Data Index: 2533827 (Open Web Text)

Max Activating Token Index: 105

Text #1

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4880. Min Act: -0.1700

Data Index: 2860086 (Open Web Text)

Max Activating Token Index: 193

Text #2

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4659. Min Act: -0.1700

Data Index: 5529775 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4670. Min Act: -0.1700

Data Index: 6969808 (Open Web Text)

Max Activating Token Index: 362

Text #4

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4577. Min Act: -0.1700

Data Index: 5378570 (Open Web Text)

Max Activating Token Index: 78

Text #5

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4371. Min Act: -0.1700

Data Index: 2533828 (Open Web Text)

Max Activating Token Index: 136

Text #6

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4336. Min Act: -0.1700

Data Index: 3854558 (Open Web Text)

Max Activating Token Index: 44

Text #7

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4292. Min Act: -0.1700

Data Index: 5613102 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4228. Min Act: -0.1671

Data Index: 1958253 (Open Web Text)

Max Activating Token Index: 191

Text #9

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4149. Min Act: -0.1700

Data Index: 5529781 (Open Web Text)

Max Activating Token Index: 23

Text #10

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4125. Min Act: -0.1700

Data Index: 5529771 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4056. Min Act: -0.1700

Data Index: 8077879 (Open Web Text)

Max Activating Token Index: 348

Text #12

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4129. Min Act: -0.1700

Data Index: 5529769 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.3994. Min Act: -0.1700

Data Index: 5529774 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.4129. Min Act: -0.1700

Data Index: 5529788 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.3953. Min Act: -0.1700

Data Index: 3856967 (Open Web Text)

Max Activating Token Index: 193

Text #16

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.3825. Min Act: -0.1700

Data Index: 4588319 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.3647. Min Act: -0.1700

Data Index: 1340228 (Open Web Text)

Max Activating Token Index: 749

Text #18

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.3770. Min Act: -0.1700

Data Index: 5529768 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 3.5343. Min Range: -3.5343

Max Act: 3.3742. Min Act: -0.1700

Data Index: 1626965 (Open Web Text)

Max Activating Token Index: 435