Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1937 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.5458. Min Act: -0.1700
Data Index: 5389698 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2333. Min Act: -0.1700
Data Index: 169352 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2333. Min Act: -0.1700
Data Index: 3650538 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.1708. Min Act: -0.1700
Data Index: 3641458 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2020. Min Act: -0.1700
Data Index: 3029126 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.0770. Min Act: -0.1700
Data Index: 3437053 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.0458. Min Act: -0.1700
Data Index: 7449819 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.0458. Min Act: -0.1700
Data Index: 5201935 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.0145. Min Act: -0.1700
Data Index: 115118 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.0145. Min Act: -0.1700
Data Index: 5717805 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.0145. Min Act: -0.1700
Data Index: 3526061 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5458. Min Range: -5.5458
Max Act: 4.9833. Min Act: -0.1700
Data Index: 2183724 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.0145. Min Act: -0.1700
Data Index: 1123081 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.0145. Min Act: -0.1700
Data Index: 6507723 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.0145. Min Act: -0.1700
Data Index: 893215 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5458. Min Range: -5.5458
Max Act: 4.9833. Min Act: -0.1700
Data Index: 4610967 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5458. Min Range: -5.5458
Max Act: 4.9833. Min Act: -0.1700
Data Index: 3295456 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5458. Min Range: -5.5458
Max Act: 4.9833. Min Act: -0.1700
Data Index: 2091453 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5458. Min Range: -5.5458
Max Act: 4.9833. Min Act: -0.1700
Data Index: 3332662 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5458. Min Range: -5.5458
Max Act: 4.9833. Min Act: -0.1700
Data Index: 1519618 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19