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

Dataset: Open Web Text

Neuron 1136 in Layer 4

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: 3.6046. Min Range: -3.6046

Max Act: 3.5935. Min Act: -0.1700

Data Index: 1295866 (Open Web Text)

Max Activating Token Index: 608

Text #1

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.6046. Min Act: -0.1700

Data Index: 5242343 (Open Web Text)

Max Activating Token Index: 76

Text #2

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.6021. Min Act: -0.1700

Data Index: 122636 (Open Web Text)

Max Activating Token Index: 369

Text #3

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5690. Min Act: -0.1700

Data Index: 8233553 (Open Web Text)

Max Activating Token Index: 120

Text #4

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5603. Min Act: -0.1700

Data Index: 7391994 (Open Web Text)

Max Activating Token Index: 861

Text #5

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5489. Min Act: -0.1700

Data Index: 7083198 (Open Web Text)

Max Activating Token Index: 857

Text #6

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5556. Min Act: -0.1700

Data Index: 66627 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5330. Min Act: -0.1700

Data Index: 2805207 (Open Web Text)

Max Activating Token Index: 883

Text #8

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5479. Min Act: -0.1700

Data Index: 6521731 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5137. Min Act: -0.1700

Data Index: 4596131 (Open Web Text)

Max Activating Token Index: 967

Text #10

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5250. Min Act: -0.1700

Data Index: 5270963 (Open Web Text)

Max Activating Token Index: 325

Text #11

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5245. Min Act: -0.1700

Data Index: 5048283 (Open Web Text)

Max Activating Token Index: 182

Text #12

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5292. Min Act: -0.1700

Data Index: 7252162 (Open Web Text)

Max Activating Token Index: 210

Text #13

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.4988. Min Act: -0.1700

Data Index: 5128694 (Open Web Text)

Max Activating Token Index: 436

Text #14

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5203. Min Act: -0.1700

Data Index: 5839191 (Open Web Text)

Max Activating Token Index: 829

Text #15

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5147. Min Act: -0.1700

Data Index: 6392826 (Open Web Text)

Max Activating Token Index: 205

Text #16

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5041. Min Act: -0.1700

Data Index: 2023091 (Open Web Text)

Max Activating Token Index: 141

Text #17

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.4971. Min Act: -0.1700

Data Index: 961233 (Open Web Text)

Max Activating Token Index: 768

Text #18

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.4912. Min Act: -0.1700

Data Index: 3672403 (Open Web Text)

Max Activating Token Index: 42

Text #19

Max Range: 3.6046. Min Range: -3.6046

Max Act: 3.5018. Min Act: -0.1700

Data Index: 4356011 (Open Web Text)

Max Activating Token Index: 653