Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6288. Min Range: -8.6288
Max Act: 8.6288. Min Act: -0.1700
Data Index: 6969600 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6288. Min Range: -8.6288
Max Act: 8.2538. Min Act: -0.1700
Data Index: 7457392 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6288. Min Range: -8.6288
Max Act: 8.1913. Min Act: -0.1700
Data Index: 7797468 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6288. Min Range: -8.6288
Max Act: 8.0663. Min Act: -0.1700
Data Index: 2771486 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.8788. Min Act: -0.1700
Data Index: 4661731 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.8163. Min Act: -0.1700
Data Index: 2141102 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.8163. Min Act: -0.1700
Data Index: 8261013 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.6913. Min Act: -0.1700
Data Index: 2627500 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.6913. Min Act: -0.1700
Data Index: 3495159 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.6600. Min Act: -0.1700
Data Index: 5681607 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.6600. Min Act: -0.1700
Data Index: 4149017 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.6288. Min Act: -0.1700
Data Index: 2417403 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.6288. Min Act: -0.1700
Data Index: 3091612 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.6600. Min Act: -0.1700
Data Index: 392948 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.5663. Min Act: -0.1700
Data Index: 6303578 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.5350. Min Act: -0.1700
Data Index: 2809946 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.5350. Min Act: -0.1700
Data Index: 1994341 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.5038. Min Act: -0.1700
Data Index: 2605493 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.5038. Min Act: -0.1700
Data Index: 7595720 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6288. Min Range: -8.6288
Max Act: 7.5038. Min Act: -0.1700
Data Index: 1597278 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19