Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1073 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0650. Min Act: -0.1700
Data Index: 1604255 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0025. Min Act: -0.1700
Data Index: 6540392 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0025. Min Act: -0.1700
Data Index: 5314962 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8775. Min Act: -0.1700
Data Index: 3598073 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9087. Min Act: -0.1700
Data Index: 8069417 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8462. Min Act: -0.1700
Data Index: 8550583 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8462. Min Act: -0.1700
Data Index: 6075174 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 421469 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 8266231 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 6377374 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7837. Min Act: -0.1700
Data Index: 229598 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 5529653 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 3240224 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 261602 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7837. Min Act: -0.1700
Data Index: 4062521 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7837. Min Act: -0.1700
Data Index: 3579861 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 1229850 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 694006 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 7653344 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 7172074 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19