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

Dataset: Open Web Text

Neuron 2414 in Layer 6

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: 3.0986. Min Range: -3.0986

Max Act: 3.0986. Min Act: -0.1700

Data Index: 6133185 (Open Web Text)

Max Activating Token Index: 103

Text #1

Max Range: 3.0986. Min Range: -3.0986

Max Act: 3.0490. Min Act: -0.1700

Data Index: 3152186 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.9884. Min Act: -0.1700

Data Index: 694042 (Open Web Text)

Max Activating Token Index: 354

Text #3

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.9248. Min Act: -0.1700

Data Index: 8832192 (Open Web Text)

Max Activating Token Index: 805

Text #4

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.9327. Min Act: -0.1700

Data Index: 3929913 (Open Web Text)

Max Activating Token Index: 941

Text #5

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.9036. Min Act: -0.1700

Data Index: 5247724 (Open Web Text)

Max Activating Token Index: 989

Text #6

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.9097. Min Act: -0.1700

Data Index: 5738976 (Open Web Text)

Max Activating Token Index: 296

Text #7

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.9174. Min Act: -0.1700

Data Index: 5334471 (Open Web Text)

Max Activating Token Index: 270

Text #8

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.9079. Min Act: -0.1700

Data Index: 8689744 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8717. Min Act: -0.1700

Data Index: 8760759 (Open Web Text)

Max Activating Token Index: 899

Text #10

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8953. Min Act: -0.1700

Data Index: 7169517 (Open Web Text)

Max Activating Token Index: 473

Text #11

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8855. Min Act: -0.1700

Data Index: 7310587 (Open Web Text)

Max Activating Token Index: 267

Text #12

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8950. Min Act: -0.1700

Data Index: 834375 (Open Web Text)

Max Activating Token Index: 935

Text #13

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8667. Min Act: -0.1700

Data Index: 2330622 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8945. Min Act: -0.1700

Data Index: 911990 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8795. Min Act: -0.1700

Data Index: 3962609 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8594. Min Act: -0.1700

Data Index: 1353954 (Open Web Text)

Max Activating Token Index: 173

Text #17

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8690. Min Act: -0.1700

Data Index: 8284042 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8583. Min Act: -0.1700

Data Index: 8300395 (Open Web Text)

Max Activating Token Index: 302

Text #19

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8416. Min Act: -0.1700

Data Index: 6583177 (Open Web Text)

Max Activating Token Index: 992