Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5348 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.6514. Min Act: -0.1700
Data Index: 2761968 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.5577. Min Act: -0.1700
Data Index: 2056682 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.5577. Min Act: -0.1700
Data Index: 3505368 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.5577. Min Act: -0.1700
Data Index: 2990040 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4952. Min Act: -0.1700
Data Index: 8544708 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.5264. Min Act: -0.1700
Data Index: 5585615 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4952. Min Act: -0.1700
Data Index: 3134394 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4952. Min Act: -0.1700
Data Index: 4690105 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4639. Min Act: -0.1700
Data Index: 1850288 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4639. Min Act: -0.1700
Data Index: 1119065 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4952. Min Act: -0.1700
Data Index: 7105743 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4639. Min Act: -0.1700
Data Index: 532122 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4639. Min Act: -0.1700
Data Index: 2907037 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4327. Min Act: -0.1700
Data Index: 7772666 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4639. Min Act: -0.1700
Data Index: 133312 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4327. Min Act: -0.1700
Data Index: 1232282 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4327. Min Act: -0.1700
Data Index: 8445837 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4327. Min Act: -0.1700
Data Index: 7611178 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4327. Min Act: -0.1700
Data Index: 2737934 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6514. Min Range: -5.6514
Max Act: 5.4327. Min Act: -0.1700
Data Index: 7426305 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19