Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5106 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2961. Min Range: -7.2961
Max Act: 7.2961. Min Act: -0.1700
Data Index: 6953436 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2961. Min Range: -7.2961
Max Act: 7.2336. Min Act: -0.1700
Data Index: 6229795 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.8899. Min Act: -0.1700
Data Index: 1805041 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.6711. Min Act: -0.1700
Data Index: 2630567 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.6711. Min Act: -0.1700
Data Index: 7599912 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.5774. Min Act: -0.1700
Data Index: 3321060 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.5149. Min Act: -0.1700
Data Index: 7710711 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.4524. Min Act: -0.1700
Data Index: 2522868 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.4211. Min Act: -0.1700
Data Index: 8748007 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.4211. Min Act: -0.1700
Data Index: 3484048 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.4211. Min Act: -0.1700
Data Index: 4211901 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.3899. Min Act: -0.1700
Data Index: 3796411 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.3586. Min Act: -0.1700
Data Index: 8823999 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.3586. Min Act: -0.1700
Data Index: 340204 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.3586. Min Act: -0.1700
Data Index: 8013082 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.3274. Min Act: -0.1700
Data Index: 6043436 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.3274. Min Act: -0.1700
Data Index: 5128513 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.3274. Min Act: -0.1700
Data Index: 7538347 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.3274. Min Act: -0.1700
Data Index: 7024123 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2961. Min Range: -7.2961
Max Act: 6.2961. Min Act: -0.1700
Data Index: 6221760 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19