Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.9593. Min Act: -0.1700
Data Index: 709722 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.9281. Min Act: -0.1700
Data Index: 5161143 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.9593. Min Act: -0.1700
Data Index: 5669306 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.8031. Min Act: -0.1700
Data Index: 7026607 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.7093. Min Act: -0.1700
Data Index: 4477982 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.7406. Min Act: -0.1700
Data Index: 3427650 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.6781. Min Act: -0.1700
Data Index: 417626 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.6468. Min Act: -0.1700
Data Index: 638749 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.6781. Min Act: -0.1700
Data Index: 466548 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.6781. Min Act: -0.1700
Data Index: 2847826 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.6156. Min Act: -0.1700
Data Index: 1868031 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.6156. Min Act: -0.1700
Data Index: 3997633 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.5843. Min Act: -0.1700
Data Index: 2340622 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.5843. Min Act: -0.1700
Data Index: 948599 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.5531. Min Act: -0.1700
Data Index: 8268578 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.5843. Min Act: -0.1700
Data Index: 2252309 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.6156. Min Act: -0.1700
Data Index: 2213322 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.5843. Min Act: -0.1700
Data Index: 2604807 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.5843. Min Act: -0.1700
Data Index: 3048139 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9593. Min Range: -5.9593
Max Act: 5.5218. Min Act: -0.1700
Data Index: 762337 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19