Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4158 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0908. Min Range: -6.0908
Max Act: 6.0908. Min Act: -0.1700
Data Index: 4114131 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.7783. Min Act: -0.1700
Data Index: 1869953 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.6845. Min Act: -0.1700
Data Index: 855639 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.6220. Min Act: -0.1700
Data Index: 5391910 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.5283. Min Act: -0.1700
Data Index: 3777918 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.5595. Min Act: -0.1700
Data Index: 2676311 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.5595. Min Act: -0.1700
Data Index: 1323550 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.4970. Min Act: -0.1700
Data Index: 3392800 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.5283. Min Act: -0.1700
Data Index: 525260 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.5283. Min Act: -0.1700
Data Index: 997114 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.5283. Min Act: -0.1700
Data Index: 4202134 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.4658. Min Act: -0.1700
Data Index: 8607245 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.4658. Min Act: -0.1700
Data Index: 6008621 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.4345. Min Act: -0.1700
Data Index: 2233218 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.4033. Min Act: -0.1700
Data Index: 1442679 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.4033. Min Act: -0.1700
Data Index: 5186015 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.4033. Min Act: -0.1700
Data Index: 421208 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.3720. Min Act: -0.1700
Data Index: 5973678 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.3720. Min Act: -0.1700
Data Index: 2740172 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0908. Min Range: -6.0908
Max Act: 5.3720. Min Act: -0.1700
Data Index: 2480800 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19