Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0530. Min Range: -6.0530
Max Act: 6.0530. Min Act: -0.1700
Data Index: 2846909 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.8342. Min Act: -0.1700
Data Index: 4372441 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.7717. Min Act: -0.1700
Data Index: 32511 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.7717. Min Act: -0.1700
Data Index: 530072 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.6780. Min Act: -0.1700
Data Index: 1424768 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.6155. Min Act: -0.1700
Data Index: 7791448 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.6155. Min Act: -0.1700
Data Index: 6657893 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5842. Min Act: -0.1700
Data Index: 1940593 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5842. Min Act: -0.1700
Data Index: 5573165 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5530. Min Act: -0.1700
Data Index: 1144995 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5530. Min Act: -0.1700
Data Index: 729287 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5530. Min Act: -0.1700
Data Index: 8338371 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5530. Min Act: -0.1700
Data Index: 511579 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5530. Min Act: -0.1700
Data Index: 1833671 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5842. Min Act: -0.1700
Data Index: 6692068 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5217. Min Act: -0.1700
Data Index: 2399355 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5217. Min Act: -0.1700
Data Index: 192831 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5217. Min Act: -0.1700
Data Index: 6377776 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5217. Min Act: -0.1700
Data Index: 4678589 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0530. Min Range: -6.0530
Max Act: 5.5217. Min Act: -0.1700
Data Index: 7559500 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19