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

Dataset: Open Web Text

Neuron 1181 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: 3.5404. Min Range: -3.5404

Max Act: 3.5377. Min Act: -0.1700

Data Index: 6733895 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.5331. Min Act: -0.1700

Data Index: 5026968 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.5376. Min Act: -0.1700

Data Index: 3436555 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.5404. Min Act: -0.1700

Data Index: 1753932 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.5162. Min Act: -0.1700

Data Index: 5866444 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.5179. Min Act: -0.1700

Data Index: 2994107 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.5120. Min Act: -0.1700

Data Index: 1161362 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.5189. Min Act: -0.1700

Data Index: 1619447 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4956. Min Act: -0.1700

Data Index: 1554806 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.5081. Min Act: -0.1700

Data Index: 3187259 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4895. Min Act: -0.1700

Data Index: 3595589 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4887. Min Act: -0.1700

Data Index: 2333552 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4740. Min Act: -0.1700

Data Index: 3036720 (Open Web Text)

Max Activating Token Index: 239

Text #13

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4788. Min Act: -0.1700

Data Index: 2240145 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4753. Min Act: -0.1700

Data Index: 6528961 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4582. Min Act: -0.1700

Data Index: 1307884 (Open Web Text)

Max Activating Token Index: 944

Text #16

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4638. Min Act: -0.1700

Data Index: 7796544 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4532. Min Act: -0.1700

Data Index: 6343395 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4624. Min Act: -0.1700

Data Index: 6540443 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.5404. Min Range: -3.5404

Max Act: 3.4415. Min Act: -0.1700

Data Index: 4580434 (Open Web Text)

Max Activating Token Index: 5