Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1748 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0552. Min Range: -4.0552
Max Act: 4.0552. Min Act: -0.1700
Data Index: 7293197 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.9927. Min Act: -0.1700
Data Index: 6021326 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.9927. Min Act: -0.1700
Data Index: 779040 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.9615. Min Act: -0.1700
Data Index: 3988583 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.9615. Min Act: -0.1700
Data Index: 5966237 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.9615. Min Act: -0.1700
Data Index: 6181388 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.8989. Min Act: -0.1700
Data Index: 2870745 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.8677. Min Act: -0.1700
Data Index: 8675469 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.8051. Min Act: -0.1700
Data Index: 6483086 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.7738. Min Act: -0.1700
Data Index: 4736195 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.7738. Min Act: -0.1700
Data Index: 5914802 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.7738. Min Act: -0.1700
Data Index: 3299017 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.8051. Min Act: -0.1700
Data Index: 6446548 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.7426. Min Act: -0.1700
Data Index: 3509819 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.7426. Min Act: -0.1700
Data Index: 946699 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.7426. Min Act: -0.1700
Data Index: 6702031 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.7426. Min Act: -0.1700
Data Index: 3557544 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.7426. Min Act: -0.1700
Data Index: 7106057 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.7113. Min Act: -0.1700
Data Index: 3854073 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0552. Min Range: -4.0552
Max Act: 3.7426. Min Act: -0.1700
Data Index: 7902245 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19