Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6391 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.5619. Min Act: -0.1700
Data Index: 2934655 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.4994. Min Act: -0.1700
Data Index: 575428 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.4056. Min Act: -0.1700
Data Index: 2382532 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.3744. Min Act: -0.1700
Data Index: 2366453 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.3119. Min Act: -0.1700
Data Index: 734965 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.3431. Min Act: -0.1700
Data Index: 1157223 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2494. Min Act: -0.1700
Data Index: 6564141 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.3119. Min Act: -0.1700
Data Index: 3511838 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2494. Min Act: -0.1700
Data Index: 1889191 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2494. Min Act: -0.1700
Data Index: 4749911 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2494. Min Act: -0.1700
Data Index: 3791460 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2494. Min Act: -0.1700
Data Index: 4314435 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2494. Min Act: -0.1700
Data Index: 7678275 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2494. Min Act: -0.1700
Data Index: 2783638 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2181. Min Act: -0.1700
Data Index: 4203385 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2181. Min Act: -0.1700
Data Index: 6911654 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2181. Min Act: -0.1700
Data Index: 5621331 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2181. Min Act: -0.1700
Data Index: 4501408 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2181. Min Act: -0.1700
Data Index: 2040928 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5619. Min Range: -6.5619
Max Act: 6.2181. Min Act: -0.1700
Data Index: 5857274 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19