Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1890. Min Range: -8.1890
Max Act: 8.1890. Min Act: -0.1700
Data Index: 1147046 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1890. Min Range: -8.1890
Max Act: 8.0328. Min Act: -0.1700
Data Index: 1795230 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.9703. Min Act: -0.1700
Data Index: 3677606 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.9078. Min Act: -0.1700
Data Index: 8475267 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.8765. Min Act: -0.1700
Data Index: 5702880 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.8140. Min Act: -0.1700
Data Index: 3268699 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.7515. Min Act: -0.1700
Data Index: 3376270 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.6890. Min Act: -0.1700
Data Index: 8306922 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.6578. Min Act: -0.1700
Data Index: 2107031 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.6890. Min Act: -0.1700
Data Index: 3500431 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.5953. Min Act: -0.1700
Data Index: 5588077 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.5953. Min Act: -0.1700
Data Index: 4695307 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.5953. Min Act: -0.1700
Data Index: 6270175 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.5953. Min Act: -0.1700
Data Index: 2391848 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.5640. Min Act: -0.1700
Data Index: 3262868 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.5328. Min Act: -0.1700
Data Index: 8332191 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.5328. Min Act: -0.1700
Data Index: 2107032 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.5328. Min Act: -0.1700
Data Index: 5901091 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.5015. Min Act: -0.1700
Data Index: 5524095 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1890. Min Range: -8.1890
Max Act: 7.4703. Min Act: -0.1700
Data Index: 5898961 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19