Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.3688. Min Act: -0.1700
Data Index: 1019263 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.3063. Min Act: -0.1700
Data Index: 1534637 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.2751. Min Act: -0.1700
Data Index: 7806929 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.2438. Min Act: -0.1700
Data Index: 1699091 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.2438. Min Act: -0.1700
Data Index: 4700832 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.2438. Min Act: -0.1700
Data Index: 7185439 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.2126. Min Act: -0.1700
Data Index: 2883938 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1813. Min Act: -0.1700
Data Index: 6766537 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1813. Min Act: -0.1700
Data Index: 2707338 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1813. Min Act: -0.1700
Data Index: 7898089 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1813. Min Act: -0.1700
Data Index: 7786878 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1501. Min Act: -0.1700
Data Index: 4317559 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1501. Min Act: -0.1700
Data Index: 5624911 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1501. Min Act: -0.1700
Data Index: 3818852 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1501. Min Act: -0.1700
Data Index: 2976358 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1501. Min Act: -0.1700
Data Index: 5909695 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1501. Min Act: -0.1700
Data Index: 3418940 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1501. Min Act: -0.1700
Data Index: 2429383 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1501. Min Act: -0.1700
Data Index: 7257871 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3688. Min Range: -5.3688
Max Act: 5.1188. Min Act: -0.1700
Data Index: 3183589 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19