Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1648. Min Range: -8.1648
Max Act: 8.1648. Min Act: -0.1700
Data Index: 6928376 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.8523. Min Act: -0.1700
Data Index: 5442550 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.7898. Min Act: -0.1700
Data Index: 3806848 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.5398. Min Act: -0.1700
Data Index: 6437328 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.6023. Min Act: -0.1700
Data Index: 3578217 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.6023. Min Act: -0.1700
Data Index: 1779963 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.5398. Min Act: -0.1700
Data Index: 5923516 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.5398. Min Act: -0.1700
Data Index: 7288858 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.5398. Min Act: -0.1700
Data Index: 3419352 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.4773. Min Act: -0.1700
Data Index: 5937352 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.4773. Min Act: -0.1700
Data Index: 190541 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.4460. Min Act: -0.1700
Data Index: 6287025 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.4460. Min Act: -0.1700
Data Index: 2423099 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.4460. Min Act: -0.1700
Data Index: 8788257 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.4460. Min Act: -0.1700
Data Index: 7196754 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.4460. Min Act: -0.1700
Data Index: 5772675 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.4148. Min Act: -0.1700
Data Index: 2995584 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.4148. Min Act: -0.1700
Data Index: 4343208 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.4460. Min Act: -0.1700
Data Index: 499941 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1648. Min Range: -8.1648
Max Act: 7.3835. Min Act: -0.1700
Data Index: 6125451 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19