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

Dataset: Open Web Text

Neuron 2705 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: 3.3895. Min Range: -3.3895

Max Act: 3.3737. Min Act: -0.1700

Data Index: 6884560 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.3895. Min Act: -0.1700

Data Index: 5654968 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.3471. Min Act: -0.1700

Data Index: 1040650 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.3073. Min Act: -0.1700

Data Index: 3289373 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2687. Min Act: -0.1700

Data Index: 1234634 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2947. Min Act: -0.1700

Data Index: 6833303 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2619. Min Act: -0.1700

Data Index: 1228307 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2691. Min Act: -0.1700

Data Index: 8184235 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2451. Min Act: -0.1700

Data Index: 4456447 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2605. Min Act: -0.1700

Data Index: 3107372 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2450. Min Act: -0.1700

Data Index: 8380743 (Open Web Text)

Max Activating Token Index: 425

Text #11

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2048. Min Act: -0.1700

Data Index: 939011 (Open Web Text)

Max Activating Token Index: 380

Text #12

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2198. Min Act: -0.1700

Data Index: 1146450 (Open Web Text)

Max Activating Token Index: 50

Text #13

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2265. Min Act: -0.1700

Data Index: 2465829 (Open Web Text)

Max Activating Token Index: 958

Text #14

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2068. Min Act: -0.1700

Data Index: 1951085 (Open Web Text)

Max Activating Token Index: 89

Text #15

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2198. Min Act: -0.1700

Data Index: 7392334 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2137. Min Act: -0.1700

Data Index: 7645423 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2227. Min Act: -0.1700

Data Index: 3058193 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2307. Min Act: -0.1700

Data Index: 7849459 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.3895. Min Range: -3.3895

Max Act: 3.2225. Min Act: -0.1700

Data Index: 8032963 (Open Web Text)

Max Activating Token Index: 25