Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 774 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.6685. Min Act: -0.1700
Data Index: 3357525 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.6372. Min Act: -0.1700
Data Index: 5951093 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.4497. Min Act: -0.1700
Data Index: 6733216 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.4497. Min Act: -0.1700
Data Index: 1363036 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.4497. Min Act: -0.1700
Data Index: 3357533 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.4185. Min Act: -0.1700
Data Index: 5645141 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.3872. Min Act: -0.1700
Data Index: 1631285 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.3247. Min Act: -0.1700
Data Index: 1363031 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.3560. Min Act: -0.1700
Data Index: 3357550 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.2622. Min Act: -0.1700
Data Index: 6263430 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.1997. Min Act: -0.1700
Data Index: 6509622 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.1060. Min Act: -0.1700
Data Index: 1363033 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.1372. Min Act: -0.1700
Data Index: 8080752 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.1997. Min Act: -0.1700
Data Index: 2680639 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.1372. Min Act: -0.1700
Data Index: 6853729 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.1060. Min Act: -0.1700
Data Index: 4302785 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.0435. Min Act: -0.1700
Data Index: 6783214 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.0122. Min Act: -0.1700
Data Index: 1920482 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6685. Min Range: -5.6685
Max Act: 5.0122. Min Act: -0.1700
Data Index: 6948543 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6685. Min Range: -5.6685
Max Act: 4.9810. Min Act: -0.1700
Data Index: 2434487 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19