Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 649 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.4122. Min Act: -0.1700
Data Index: 7651153 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.1309. Min Act: -0.1700
Data Index: 3875770 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.1309. Min Act: -0.1700
Data Index: 2662753 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.1309. Min Act: -0.1700
Data Index: 5808773 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 4101397 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 8673353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 748300 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 8661008 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 6434041 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 8384406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 7285068 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 1796311 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 649942 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 3185289 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 7059879 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 3104023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 3064439 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 8163989 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 5669177 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4122. Min Range: -4.4122
Max Act: 4.0684. Min Act: -0.1700
Data Index: 5132161 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19