Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1475 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1653. Min Range: -3.1653
Max Act: 3.1653. Min Act: -0.1700
Data Index: 871722 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1653. Min Range: -3.1653
Max Act: 3.0076. Min Act: -0.1700
Data Index: 4603482 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.9601. Min Act: -0.1700
Data Index: 5670143 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.8650. Min Act: -0.1700
Data Index: 7595904 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.8492. Min Act: -0.1700
Data Index: 1945586 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.8492. Min Act: -0.1700
Data Index: 7951317 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.8174. Min Act: -0.1700
Data Index: 5177648 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.8174. Min Act: -0.1700
Data Index: 2569369 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.8174. Min Act: -0.1700
Data Index: 952805 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.8014. Min Act: -0.1700
Data Index: 5254813 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.7696. Min Act: -0.1700
Data Index: 6437722 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.8014. Min Act: -0.1700
Data Index: 8200740 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.7696. Min Act: -0.1700
Data Index: 4687255 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.7696. Min Act: -0.1700
Data Index: 6964978 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.7696. Min Act: -0.1700
Data Index: 4910309 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.7376. Min Act: -0.1700
Data Index: 1828775 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.7536. Min Act: -0.1700
Data Index: 379428 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.7536. Min Act: -0.1700
Data Index: 2050468 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.7536. Min Act: -0.1700
Data Index: 1346084 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1653. Min Range: -3.1653
Max Act: 2.7376. Min Act: -0.1700
Data Index: 7268554 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19