Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5461 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8029. Min Range: -8.8029
Max Act: 8.8029. Min Act: -0.1700
Data Index: 618215 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8029. Min Range: -8.8029
Max Act: 8.5529. Min Act: -0.1700
Data Index: 7869761 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8029. Min Range: -8.8029
Max Act: 8.3029. Min Act: -0.1700
Data Index: 2251008 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8029. Min Range: -8.8029
Max Act: 8.2404. Min Act: -0.1700
Data Index: 3854894 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8029. Min Range: -8.8029
Max Act: 8.1779. Min Act: -0.1700
Data Index: 3732695 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8029. Min Range: -8.8029
Max Act: 8.0529. Min Act: -0.1700
Data Index: 7250178 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.9904. Min Act: -0.1700
Data Index: 2870181 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.9904. Min Act: -0.1700
Data Index: 6851137 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.8654. Min Act: -0.1700
Data Index: 7596409 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.8654. Min Act: -0.1700
Data Index: 6687553 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.7404. Min Act: -0.1700
Data Index: 2405257 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.8029. Min Act: -0.1700
Data Index: 6951572 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.8029. Min Act: -0.1700
Data Index: 2197958 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.8029. Min Act: -0.1700
Data Index: 1013130 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.8029. Min Act: -0.1700
Data Index: 161458 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.7404. Min Act: -0.1700
Data Index: 280570 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.7404. Min Act: -0.1700
Data Index: 766252 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.7404. Min Act: -0.1700
Data Index: 3171077 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.6779. Min Act: -0.1700
Data Index: 4986203 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8029. Min Range: -8.8029
Max Act: 7.6779. Min Act: -0.1700
Data Index: 5127932 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19