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

Dataset: Open Web Text

Neuron 298 in Layer 0

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: 4.0530. Min Range: -4.0530

Max Act: 4.0530. Min Act: -0.1700

Data Index: 3728177 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.8569. Min Act: -0.1700

Data Index: 3017955 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.8622. Min Act: -0.1700

Data Index: 1372378 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.8224. Min Act: -0.1700

Data Index: 1119343 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.8290. Min Act: -0.1700

Data Index: 2520563 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.8489. Min Act: -0.1700

Data Index: 5228158 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.8147. Min Act: -0.1700

Data Index: 3567823 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.7941. Min Act: -0.1700

Data Index: 6595002 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.8135. Min Act: -0.1700

Data Index: 7099991 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.7676. Min Act: -0.1700

Data Index: 2275116 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.7732. Min Act: -0.1700

Data Index: 4918981 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.7632. Min Act: -0.1700

Data Index: 2885810 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.7456. Min Act: -0.1700

Data Index: 4977410 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.6912. Min Act: -0.1700

Data Index: 3406647 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.6627. Min Act: -0.1700

Data Index: 543734 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.6855. Min Act: -0.1700

Data Index: 8511221 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.6557. Min Act: -0.1700

Data Index: 7842396 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.6535. Min Act: -0.1700

Data Index: 5970464 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.6258. Min Act: -0.1700

Data Index: 2971059 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 4.0530. Min Range: -4.0530

Max Act: 3.6230. Min Act: -0.1700

Data Index: 4912161 (Open Web Text)

Max Activating Token Index: 9