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

Dataset: Open Web Text

Neuron 2586 in Layer 5

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: 3.3079. Min Range: -3.3079

Max Act: 3.3079. Min Act: -0.1700

Data Index: 589721 (Open Web Text)

Max Activating Token Index: 64

Text #1

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.1548. Min Act: -0.1700

Data Index: 5690808 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.1184. Min Act: -0.1700

Data Index: 8479809 (Open Web Text)

Max Activating Token Index: 175

Text #3

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.1043. Min Act: -0.1700

Data Index: 8537344 (Open Web Text)

Max Activating Token Index: 931

Text #4

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.0439. Min Act: -0.1700

Data Index: 5961052 (Open Web Text)

Max Activating Token Index: 582

Text #5

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.0605. Min Act: -0.1700

Data Index: 4925812 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.0576. Min Act: -0.1700

Data Index: 4628441 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.0166. Min Act: -0.1700

Data Index: 4215585 (Open Web Text)

Max Activating Token Index: 946

Text #8

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.0260. Min Act: -0.1700

Data Index: 4312971 (Open Web Text)

Max Activating Token Index: 446

Text #9

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.0203. Min Act: -0.1700

Data Index: 2994309 (Open Web Text)

Max Activating Token Index: 939

Text #10

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.0199. Min Act: -0.1700

Data Index: 2830082 (Open Web Text)

Max Activating Token Index: 950

Text #11

Max Range: 3.3079. Min Range: -3.3079

Max Act: 2.9963. Min Act: -0.1700

Data Index: 6675619 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.0141. Min Act: -0.1700

Data Index: 582524 (Open Web Text)

Max Activating Token Index: 740

Text #13

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.0233. Min Act: -0.1700

Data Index: 1093807 (Open Web Text)

Max Activating Token Index: 697

Text #14

Max Range: 3.3079. Min Range: -3.3079

Max Act: 2.9871. Min Act: -0.1700

Data Index: 1119048 (Open Web Text)

Max Activating Token Index: 826

Text #15

Max Range: 3.3079. Min Range: -3.3079

Max Act: 3.0061. Min Act: -0.1700

Data Index: 8239170 (Open Web Text)

Max Activating Token Index: 575

Text #16

Max Range: 3.3079. Min Range: -3.3079

Max Act: 2.9895. Min Act: -0.1700

Data Index: 2342120 (Open Web Text)

Max Activating Token Index: 100

Text #17

Max Range: 3.3079. Min Range: -3.3079

Max Act: 2.9851. Min Act: -0.1700

Data Index: 7151314 (Open Web Text)

Max Activating Token Index: 118

Text #18

Max Range: 3.3079. Min Range: -3.3079

Max Act: 2.9762. Min Act: -0.1700

Data Index: 2809608 (Open Web Text)

Max Activating Token Index: 467

Text #19

Max Range: 3.3079. Min Range: -3.3079

Max Act: 2.9742. Min Act: -0.1700

Data Index: 477127 (Open Web Text)

Max Activating Token Index: 645