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

Dataset: Open Web Text

Neuron 2070 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: 4.8951. Min Range: -4.8951

Max Act: 4.8951. Min Act: -0.1700

Data Index: 89076 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.8839. Min Act: -0.1700

Data Index: 6825631 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.8462. Min Act: -0.1700

Data Index: 6268458 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.8402. Min Act: -0.1700

Data Index: 6820051 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.8681. Min Act: -0.1700

Data Index: 6186522 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.8235. Min Act: -0.1700

Data Index: 580671 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.8286. Min Act: -0.1700

Data Index: 141529 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.8141. Min Act: -0.1700

Data Index: 7322269 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.8139. Min Act: -0.1700

Data Index: 5659927 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.8088. Min Act: -0.1700

Data Index: 7935858 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.7937. Min Act: -0.1700

Data Index: 4894309 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.8041. Min Act: -0.1700

Data Index: 1780018 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.7778. Min Act: -0.1700

Data Index: 4543271 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.7572. Min Act: -0.1700

Data Index: 1508315 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.7706. Min Act: -0.1700

Data Index: 7964370 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.7701. Min Act: -0.1700

Data Index: 7897224 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.7893. Min Act: -0.1700

Data Index: 7188796 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.7435. Min Act: -0.1700

Data Index: 1614836 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.7353. Min Act: -0.1700

Data Index: 5200212 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.8951. Min Range: -4.8951

Max Act: 4.7627. Min Act: -0.1700

Data Index: 5724622 (Open Web Text)

Max Activating Token Index: 5