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

Dataset: Open Web Text

Neuron 82 in Layer 1

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: 1.8081. Min Range: -1.8081

Max Act: 1.8081. Min Act: -0.1700

Data Index: 6087657 (Open Web Text)

Max Activating Token Index: 191

Text #1

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7980. Min Act: -0.1700

Data Index: 5189922 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7739. Min Act: -0.1700

Data Index: 4280617 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7703. Min Act: -0.1700

Data Index: 5474257 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7666. Min Act: -0.1700

Data Index: 3479807 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7506. Min Act: -0.1698

Data Index: 2704056 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7553. Min Act: -0.1700

Data Index: 6169074 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7539. Min Act: -0.1700

Data Index: 1912578 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7436. Min Act: -0.1700

Data Index: 6409540 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7567. Min Act: -0.1700

Data Index: 5978993 (Open Web Text)

Max Activating Token Index: 38

Text #10

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7505. Min Act: -0.1700

Data Index: 7199797 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7348. Min Act: -0.1700

Data Index: 4382335 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7335. Min Act: -0.1700

Data Index: 2183562 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7250. Min Act: -0.1700

Data Index: 3123735 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7208. Min Act: -0.1700

Data Index: 8709629 (Open Web Text)

Max Activating Token Index: 422

Text #15

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7289. Min Act: -0.1700

Data Index: 8505494 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7218. Min Act: -0.1700

Data Index: 3411488 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7304. Min Act: -0.1700

Data Index: 3802062 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7190. Min Act: -0.1700

Data Index: 5673317 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7207. Min Act: -0.1700

Data Index: 7792790 (Open Web Text)

Max Activating Token Index: 11