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

Dataset: Open Web Text

Neuron 962 in Layer 5

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: 3.5045. Min Range: -3.5045

Max Act: 3.5045. Min Act: -0.1700

Data Index: 3289718 (Open Web Text)

Max Activating Token Index: 1007

Text #1

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3938. Min Act: -0.1700

Data Index: 5192583 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.4044. Min Act: -0.1700

Data Index: 7953355 (Open Web Text)

Max Activating Token Index: 900

Text #3

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3621. Min Act: -0.1700

Data Index: 4201819 (Open Web Text)

Max Activating Token Index: 48

Text #4

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3267. Min Act: -0.1700

Data Index: 2194141 (Open Web Text)

Max Activating Token Index: 624

Text #5

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3357. Min Act: -0.1700

Data Index: 7602581 (Open Web Text)

Max Activating Token Index: 735

Text #6

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3547. Min Act: -0.1700

Data Index: 5159031 (Open Web Text)

Max Activating Token Index: 810

Text #7

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3346. Min Act: -0.1700

Data Index: 8547298 (Open Web Text)

Max Activating Token Index: 859

Text #8

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3246. Min Act: -0.1700

Data Index: 291705 (Open Web Text)

Max Activating Token Index: 739

Text #9

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3202. Min Act: -0.1700

Data Index: 5256958 (Open Web Text)

Max Activating Token Index: 296

Text #10

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.2971. Min Act: -0.1700

Data Index: 5816935 (Open Web Text)

Max Activating Token Index: 467

Text #11

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3007. Min Act: -0.1700

Data Index: 149268 (Open Web Text)

Max Activating Token Index: 714

Text #12

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3094. Min Act: -0.1700

Data Index: 1591722 (Open Web Text)

Max Activating Token Index: 692

Text #13

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3127. Min Act: -0.1700

Data Index: 440865 (Open Web Text)

Max Activating Token Index: 962

Text #14

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3001. Min Act: -0.1700

Data Index: 1967181 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3022. Min Act: -0.1700

Data Index: 764854 (Open Web Text)

Max Activating Token Index: 802

Text #16

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.2948. Min Act: -0.1700

Data Index: 6985675 (Open Web Text)

Max Activating Token Index: 748

Text #17

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3019. Min Act: -0.1700

Data Index: 4974598 (Open Web Text)

Max Activating Token Index: 741

Text #18

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.2916. Min Act: -0.1700

Data Index: 3125778 (Open Web Text)

Max Activating Token Index: 264

Text #19

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.2914. Min Act: -0.1700

Data Index: 5682937 (Open Web Text)

Max Activating Token Index: 930