Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4732 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.6719. Min Act: -0.1700
Data Index: 6876064 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.5469. Min Act: -0.1700
Data Index: 8042698 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.5156. Min Act: -0.1700
Data Index: 7251098 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.4844. Min Act: -0.1700
Data Index: 5953596 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.4531. Min Act: -0.1700
Data Index: 7698473 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.4531. Min Act: -0.1700
Data Index: 3675178 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.3594. Min Act: -0.1700
Data Index: 1554351 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.3594. Min Act: -0.1700
Data Index: 990404 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.3281. Min Act: -0.1700
Data Index: 2276419 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2969. Min Act: -0.1700
Data Index: 2012382 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2969. Min Act: -0.1700
Data Index: 7751526 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2656. Min Act: -0.1700
Data Index: 3622870 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2969. Min Act: -0.1700
Data Index: 4952174 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2656. Min Act: -0.1700
Data Index: 6553131 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2656. Min Act: -0.1700
Data Index: 311719 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2656. Min Act: -0.1700
Data Index: 1182649 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2344. Min Act: -0.1700
Data Index: 889407 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2656. Min Act: -0.1700
Data Index: 5647537 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2344. Min Act: -0.1700
Data Index: 4566673 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6719. Min Range: -6.6719
Max Act: 6.2344. Min Act: -0.1700
Data Index: 3767206 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19