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

Dataset: Open Web Text

Neuron 897 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: 1.7648. Min Range: -1.7648

Max Act: 1.7648. Min Act: -0.1700

Data Index: 6475755 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7338. Min Act: -0.1700

Data Index: 890049 (Open Web Text)

Max Activating Token Index: 841

Text #2

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7461. Min Act: -0.1700

Data Index: 141067 (Open Web Text)

Max Activating Token Index: 67

Text #3

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7371. Min Act: -0.1699

Data Index: 5085614 (Open Web Text)

Max Activating Token Index: 52

Text #4

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7413. Min Act: -0.1700

Data Index: 2352143 (Open Web Text)

Max Activating Token Index: 321

Text #5

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7297. Min Act: -0.1700

Data Index: 8301665 (Open Web Text)

Max Activating Token Index: 148

Text #6

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7316. Min Act: -0.1700

Data Index: 1491812 (Open Web Text)

Max Activating Token Index: 105

Text #7

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7140. Min Act: -0.1700

Data Index: 616593 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7092. Min Act: -0.1700

Data Index: 8131852 (Open Web Text)

Max Activating Token Index: 81

Text #9

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7217. Min Act: -0.1700

Data Index: 5937799 (Open Web Text)

Max Activating Token Index: 238

Text #10

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7279. Min Act: -0.1700

Data Index: 5059817 (Open Web Text)

Max Activating Token Index: 827

Text #11

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7033. Min Act: -0.1700

Data Index: 3956125 (Open Web Text)

Max Activating Token Index: 746

Text #12

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7182. Min Act: -0.1700

Data Index: 3123845 (Open Web Text)

Max Activating Token Index: 155

Text #13

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7060. Min Act: -0.1700

Data Index: 4755967 (Open Web Text)

Max Activating Token Index: 184

Text #14

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7029. Min Act: -0.1700

Data Index: 6187080 (Open Web Text)

Max Activating Token Index: 53

Text #15

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7009. Min Act: -0.1698

Data Index: 1611185 (Open Web Text)

Max Activating Token Index: 451

Text #16

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6950. Min Act: -0.1697

Data Index: 1537915 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6950. Min Act: -0.1700

Data Index: 4559147 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6977. Min Act: -0.1700

Data Index: 282951 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6886. Min Act: -0.1700

Data Index: 4231502 (Open Web Text)

Max Activating Token Index: 668