Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3211 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.6025. Min Range: -10.6025
Max Act: 10.6025. Min Act: -0.1700
Data Index: 3204759 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6025. Min Range: -10.6025
Max Act: 10.1650. Min Act: -0.1700
Data Index: 3096682 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6025. Min Range: -10.6025
Max Act: 10.1650. Min Act: -0.1700
Data Index: 1570384 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6025. Min Range: -10.6025
Max Act: 10.1650. Min Act: -0.1700
Data Index: 900067 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6025. Min Range: -10.6025
Max Act: 10.1025. Min Act: -0.1700
Data Index: 8605200 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.9775. Min Act: -0.1700
Data Index: 7973814 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.9775. Min Act: -0.1700
Data Index: 1702618 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.9775. Min Act: -0.1700
Data Index: 2836298 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.9775. Min Act: -0.1699
Data Index: 2382657 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.9150. Min Act: -0.1700
Data Index: 7074367 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.9150. Min Act: -0.1700
Data Index: 1988257 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.8525. Min Act: -0.1700
Data Index: 6206244 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.8525. Min Act: -0.1700
Data Index: 8760798 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.7275. Min Act: -0.1700
Data Index: 6417391 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.6650. Min Act: -0.1696
Data Index: 5722134 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.6650. Min Act: -0.1700
Data Index: 533533 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.6025. Min Act: -0.1700
Data Index: 5101446 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.6025. Min Act: -0.1700
Data Index: 3254161 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.5400. Min Act: -0.1700
Data Index: 3432347 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6025. Min Range: -10.6025
Max Act: 9.5400. Min Act: -0.1700
Data Index: 8059357 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19