Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5239 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.2414. Min Act: -0.1700
Data Index: 2980082 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.2100. Min Act: -0.1700
Data Index: 4635003 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.1785. Min Act: -0.1700
Data Index: 6888124 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.1470. Min Act: -0.1700
Data Index: 8463396 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.1313. Min Act: -0.1700
Data Index: 3178894 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0998. Min Act: -0.1700
Data Index: 7834547 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0998. Min Act: -0.1700
Data Index: 4377690 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0682. Min Act: -0.1700
Data Index: 7953029 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0525. Min Act: -0.1700
Data Index: 4065996 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0525. Min Act: -0.1700
Data Index: 1200473 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0525. Min Act: -0.1700
Data Index: 1312155 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0525. Min Act: -0.1700
Data Index: 150839 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0367. Min Act: -0.1700
Data Index: 4722417 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0209. Min Act: -0.1700
Data Index: 5932310 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0209. Min Act: -0.1700
Data Index: 6580655 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0367. Min Act: -0.1700
Data Index: 5820327 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0209. Min Act: -0.1700
Data Index: 198000 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0051. Min Act: -0.1700
Data Index: 1711177 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0051. Min Act: -0.1700
Data Index: 5859305 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2414. Min Range: -3.2414
Max Act: 3.0051. Min Act: -0.1700
Data Index: 723499 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19