Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2318 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.8306. Min Act: -0.1700
Data Index: 4866879 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.6431. Min Act: -0.1700
Data Index: 2817858 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.7056. Min Act: -0.1700
Data Index: 8028000 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.6431. Min Act: -0.1700
Data Index: 2473801 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.5806. Min Act: -0.1700
Data Index: 20782 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.5806. Min Act: -0.1700
Data Index: 835611 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.5181. Min Act: -0.1700
Data Index: 4108776 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.5181. Min Act: -0.1700
Data Index: 661420 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.5181. Min Act: -0.1700
Data Index: 8646350 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.4556. Min Act: -0.1700
Data Index: 1320378 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.4556. Min Act: -0.1700
Data Index: 6797370 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.4556. Min Act: -0.1700
Data Index: 4657768 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.4556. Min Act: -0.1700
Data Index: 5404958 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.4556. Min Act: -0.1700
Data Index: 6328046 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3306. Min Act: -0.1700
Data Index: 1312665 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3931. Min Act: -0.1700
Data Index: 617442 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3931. Min Act: -0.1700
Data Index: 1945235 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3931. Min Act: -0.1700
Data Index: 4206366 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3931. Min Act: -0.1700
Data Index: 2870887 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3931. Min Act: -0.1700
Data Index: 4748348 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19