Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6031 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.6164. Min Act: -0.1700
Data Index: 383057 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.0852. Min Act: -0.1700
Data Index: 7032312 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.0852. Min Act: -0.1700
Data Index: 8003383 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.0539. Min Act: -0.1700
Data Index: 5140439 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.0227. Min Act: -0.1700
Data Index: 399718 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.0227. Min Act: -0.1700
Data Index: 3345035 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.0227. Min Act: -0.1700
Data Index: 4475598 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.9602. Min Act: -0.1700
Data Index: 6295933 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.9914. Min Act: -0.1700
Data Index: 2919149 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.9914. Min Act: -0.1700
Data Index: 2622544 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.9602. Min Act: -0.1700
Data Index: 6322628 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.9602. Min Act: -0.1700
Data Index: 2677621 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.9602. Min Act: -0.1700
Data Index: 1706799 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.9289. Min Act: -0.1700
Data Index: 3723043 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.9289. Min Act: -0.1700
Data Index: 6538324 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.9289. Min Act: -0.1700
Data Index: 8830592 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.9289. Min Act: -0.1700
Data Index: 2244545 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.8977. Min Act: -0.1700
Data Index: 64469 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.8977. Min Act: -0.1700
Data Index: 4220560 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6164. Min Range: -6.6164
Max Act: 5.8352. Min Act: -0.1700
Data Index: 4485213 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19