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

Dataset: Open Web Text

Neuron 2818 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: 3.9056. Min Range: -3.9056

Max Act: 3.8781. Min Act: -0.1700

Data Index: 1115191 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8998. Min Act: -0.1700

Data Index: 1078184 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8804. Min Act: -0.1700

Data Index: 3696773 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.9056. Min Act: -0.1700

Data Index: 1423948 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8741. Min Act: -0.1700

Data Index: 7907455 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8664. Min Act: -0.1700

Data Index: 7597038 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8675. Min Act: -0.1700

Data Index: 4528468 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8193. Min Act: -0.1700

Data Index: 3653236 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8188. Min Act: -0.1700

Data Index: 4803148 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8374. Min Act: -0.1700

Data Index: 4772147 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8137. Min Act: -0.1700

Data Index: 3383615 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8324. Min Act: -0.1700

Data Index: 6706912 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8123. Min Act: -0.1700

Data Index: 5846416 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8123. Min Act: -0.1700

Data Index: 7560095 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7942. Min Act: -0.1700

Data Index: 5812413 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8123. Min Act: -0.1700

Data Index: 7473059 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8001. Min Act: -0.1700

Data Index: 2616463 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8057. Min Act: -0.1700

Data Index: 5140607 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8123. Min Act: -0.1700

Data Index: 2168186 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8123. Min Act: -0.1700

Data Index: 4064628 (Open Web Text)

Max Activating Token Index: 2