Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5037 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.4536. Min Act: -0.1700
Data Index: 7764701 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.3911. Min Act: -0.1700
Data Index: 6336627 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.3598. Min Act: -0.1700
Data Index: 1546337 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.3286. Min Act: -0.1700
Data Index: 3277218 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.3286. Min Act: -0.1700
Data Index: 4254797 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2973. Min Act: -0.1700
Data Index: 7668998 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2661. Min Act: -0.1700
Data Index: 200260 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2973. Min Act: -0.1700
Data Index: 8159731 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2973. Min Act: -0.1700
Data Index: 2727906 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2973. Min Act: -0.1700
Data Index: 1891490 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2661. Min Act: -0.1700
Data Index: 5475591 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2661. Min Act: -0.1700
Data Index: 374821 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2348. Min Act: -0.1700
Data Index: 687499 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2348. Min Act: -0.1700
Data Index: 5121238 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2036. Min Act: -0.1700
Data Index: 4421383 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.2036. Min Act: -0.1700
Data Index: 8105894 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.1723. Min Act: -0.1700
Data Index: 3524313 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.1723. Min Act: -0.1700
Data Index: 5087340 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.1411. Min Act: -0.1700
Data Index: 5134013 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4536. Min Range: -4.4536
Max Act: 4.1411. Min Act: -0.1700
Data Index: 1151910 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19