Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5898 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.3452. Min Act: -0.1700
Data Index: 4489950 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.3452. Min Act: -0.1700
Data Index: 1108854 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.3452. Min Act: -0.1700
Data Index: 7300903 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.3124. Min Act: -0.1700
Data Index: 7090710 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2959. Min Act: -0.1700
Data Index: 3247670 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2795. Min Act: -0.1700
Data Index: 8386088 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2795. Min Act: -0.1700
Data Index: 5613638 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2630. Min Act: -0.1700
Data Index: 4153124 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2630. Min Act: -0.1700
Data Index: 3205151 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2630. Min Act: -0.1700
Data Index: 3382639 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2465. Min Act: -0.1700
Data Index: 1924281 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2465. Min Act: -0.1700
Data Index: 2180216 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2465. Min Act: -0.1700
Data Index: 8211791 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2465. Min Act: -0.1700
Data Index: 8211789 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2465. Min Act: -0.1700
Data Index: 3959417 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2299. Min Act: -0.1700
Data Index: 6448747 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2299. Min Act: -0.1700
Data Index: 3734515 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2134. Min Act: -0.1700
Data Index: 7332099 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2134. Min Act: -0.1700
Data Index: 3382638 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3452. Min Range: -2.3452
Max Act: 2.2134. Min Act: -0.1700
Data Index: 8211787 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19