Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1498 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.4593. Min Act: -0.1700
Data Index: 3390583 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.4593. Min Act: -0.1700
Data Index: 1689656 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.3343. Min Act: -0.1700
Data Index: 3586468 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.2718. Min Act: -0.1700
Data Index: 3920834 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.3030. Min Act: -0.1700
Data Index: 1089242 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.2718. Min Act: -0.1700
Data Index: 791201 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.2405. Min Act: -0.1700
Data Index: 5285492 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.2093. Min Act: -0.1700
Data Index: 8094564 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.1780. Min Act: -0.1700
Data Index: 7359194 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.2093. Min Act: -0.1700
Data Index: 3482782 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.1780. Min Act: -0.1700
Data Index: 7568938 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.1468. Min Act: -0.1700
Data Index: 3088678 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.1468. Min Act: -0.1700
Data Index: 1060316 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.1155. Min Act: -0.1700
Data Index: 702635 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.1468. Min Act: -0.1700
Data Index: 231004 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.1155. Min Act: -0.1700
Data Index: 5903752 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.1155. Min Act: -0.1700
Data Index: 6042212 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.1468. Min Act: -0.1700
Data Index: 2940395 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.1155. Min Act: -0.1700
Data Index: 5040711 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4593. Min Range: -4.4593
Max Act: 4.0843. Min Act: -0.1700
Data Index: 1487919 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19