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

Dataset: Open Web Text

Neuron 1647 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: 1.4091. Min Range: -1.4091

Max Act: 1.4091. Min Act: -0.1700

Data Index: 719433 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3532. Min Act: -0.1674

Data Index: 2360324 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3581. Min Act: -0.1700

Data Index: 2930799 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3249. Min Act: -0.1697

Data Index: 1644830 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3285. Min Act: -0.1698

Data Index: 4054351 (Open Web Text)

Max Activating Token Index: 107

Text #5

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3210. Min Act: -0.1697

Data Index: 6375128 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3181. Min Act: -0.1683

Data Index: 217972 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3173. Min Act: -0.1681

Data Index: 4914189 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3136. Min Act: -0.1671

Data Index: 5060152 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3122. Min Act: -0.1679

Data Index: 1535462 (Open Web Text)

Max Activating Token Index: 96

Text #10

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3094. Min Act: -0.1658

Data Index: 1625262 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3104. Min Act: -0.1692

Data Index: 7181017 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2900. Min Act: -0.1699

Data Index: 6624371 (Open Web Text)

Max Activating Token Index: 558

Text #13

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2968. Min Act: -0.1700

Data Index: 7054191 (Open Web Text)

Max Activating Token Index: 46

Text #14

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2940. Min Act: -0.1690

Data Index: 671828 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2958. Min Act: -0.1688

Data Index: 7902656 (Open Web Text)

Max Activating Token Index: 203

Text #16

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3061. Min Act: -0.1649

Data Index: 6098675 (Open Web Text)

Max Activating Token Index: 90

Text #17

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2842. Min Act: -0.1694

Data Index: 89268 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2836. Min Act: -0.1698

Data Index: 2235299 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2864. Min Act: -0.1692

Data Index: 4383362 (Open Web Text)

Max Activating Token Index: 11