Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1923 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.6053. Min Act: -0.1698
Data Index: 2835509 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5818. Min Act: -0.1698
Data Index: 2691669 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5818. Min Act: -0.1686
Data Index: 3612884 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5740. Min Act: -0.1680
Data Index: 8739317 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5662. Min Act: -0.1700
Data Index: 4416649 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5585. Min Act: -0.1700
Data Index: 1255670 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5508. Min Act: -0.1700
Data Index: 2835516 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5431. Min Act: -0.1694
Data Index: 3612883 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5431. Min Act: -0.1699
Data Index: 990617 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5278. Min Act: -0.1699
Data Index: 8104824 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5354. Min Act: -0.1668
Data Index: 4672906 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5354. Min Act: -0.1700
Data Index: 1700512 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5126. Min Act: -0.1700
Data Index: 1723936 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5051. Min Act: -0.1699
Data Index: 2149910 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5051. Min Act: -0.1610
Data Index: 5412529 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5126. Min Act: -0.1700
Data Index: 4330375 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.4975. Min Act: -0.1697
Data Index: 2652481 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.5051. Min Act: -0.1700
Data Index: 2985896 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.4975. Min Act: -0.1700
Data Index: 5819838 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6053. Min Range: -0.6053
Max Act: 0.4975. Min Act: -0.1700
Data Index: 860344 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19