Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0954. Min Range: -2.0954
Max Act: 2.0786. Min Act: -0.1700
Data Index: 751936 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0954. Min Range: -2.0954
Max Act: 2.0954. Min Act: -0.1700
Data Index: 6019496 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0954. Min Range: -2.0954
Max Act: 2.0619. Min Act: -0.1700
Data Index: 1917148 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0954. Min Range: -2.0954
Max Act: 2.0450. Min Act: -0.1700
Data Index: 436129 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0954. Min Range: -2.0954
Max Act: 2.0282. Min Act: -0.1700
Data Index: 2660067 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0954. Min Range: -2.0954
Max Act: 2.0113. Min Act: -0.1700
Data Index: 7819742 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9775. Min Act: -0.1700
Data Index: 4940507 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9944. Min Act: -0.1700
Data Index: 436130 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9944. Min Act: -0.1700
Data Index: 6418093 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9944. Min Act: -0.1700
Data Index: 2826727 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9944. Min Act: -0.1698
Data Index: 1934518 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9775. Min Act: -0.1700
Data Index: 1201720 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9606. Min Act: -0.1700
Data Index: 5436692 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9944. Min Act: -0.1700
Data Index: 8013009 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9606. Min Act: -0.1700
Data Index: 7079683 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9775. Min Act: -0.1700
Data Index: 558756 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9606. Min Act: -0.1700
Data Index: 6148095 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9606. Min Act: -0.1700
Data Index: 5483752 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9606. Min Act: -0.1700
Data Index: 6172222 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0954. Min Range: -2.0954
Max Act: 1.9606. Min Act: -0.1700
Data Index: 1374448 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19