Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4839 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.2659. Min Act: -0.1700
Data Index: 740697 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.1408. Min Act: -0.1700
Data Index: 5547353 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.1408. Min Act: -0.1700
Data Index: 4314400 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.1096. Min Act: -0.1700
Data Index: 7019049 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.1096. Min Act: -0.1700
Data Index: 6384576 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.1096. Min Act: -0.1700
Data Index: 3124598 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.1096. Min Act: -0.1700
Data Index: 8821539 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.0783. Min Act: -0.1700
Data Index: 3589534 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.0471. Min Act: -0.1700
Data Index: 1869987 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.0158. Min Act: -0.1700
Data Index: 3818063 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2659. Min Range: -4.2659
Max Act: 4.0158. Min Act: -0.1700
Data Index: 6657742 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2659. Min Range: -4.2659
Max Act: 3.9846. Min Act: -0.1700
Data Index: 2422141 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2659. Min Range: -4.2659
Max Act: 3.9846. Min Act: -0.1700
Data Index: 1208917 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2659. Min Range: -4.2659
Max Act: 3.9533. Min Act: -0.1700
Data Index: 5145104 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2659. Min Range: -4.2659
Max Act: 3.9533. Min Act: -0.1700
Data Index: 3256179 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2659. Min Range: -4.2659
Max Act: 3.9533. Min Act: -0.1700
Data Index: 7384953 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2659. Min Range: -4.2659
Max Act: 3.9533. Min Act: -0.1700
Data Index: 1857483 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2659. Min Range: -4.2659
Max Act: 3.9533. Min Act: -0.1700
Data Index: 6505951 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2659. Min Range: -4.2659
Max Act: 3.9220. Min Act: -0.1700
Data Index: 5581041 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2659. Min Range: -4.2659
Max Act: 3.9220. Min Act: -0.1700
Data Index: 4709709 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19