Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0783. Min Range: -4.0783
Max Act: 4.0783. Min Act: -0.1700
Data Index: 1804565 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0783. Min Range: -4.0783
Max Act: 4.0157. Min Act: -0.1700
Data Index: 1281217 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0783. Min Range: -4.0783
Max Act: 4.0470. Min Act: -0.1700
Data Index: 606134 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.9845. Min Act: -0.1700
Data Index: 851888 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0783. Min Range: -4.0783
Max Act: 4.0157. Min Act: -0.1700
Data Index: 6891637 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.9845. Min Act: -0.1700
Data Index: 2551558 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.9532. Min Act: -0.1700
Data Index: 1936037 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.9532. Min Act: -0.1700
Data Index: 5317354 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.9532. Min Act: -0.1700
Data Index: 8076222 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.9220. Min Act: -0.1700
Data Index: 4193514 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.8907. Min Act: -0.1700
Data Index: 3069990 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.8907. Min Act: -0.1700
Data Index: 3744355 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.8907. Min Act: -0.1700
Data Index: 3241028 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.8594. Min Act: -0.1700
Data Index: 1524558 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.8594. Min Act: -0.1700
Data Index: 2671905 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.8594. Min Act: -0.1700
Data Index: 5602538 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.8282. Min Act: -0.1700
Data Index: 6958176 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.8282. Min Act: -0.1700
Data Index: 931880 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.8282. Min Act: -0.1700
Data Index: 74664 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0783. Min Range: -4.0783
Max Act: 3.7969. Min Act: -0.1700
Data Index: 6830860 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19