Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 931 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.5140. Min Act: -0.1700
Data Index: 8053756 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.3577. Min Act: -0.1700
Data Index: 1952351 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.2640. Min Act: -0.1700
Data Index: 4258088 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1702. Min Act: -0.1700
Data Index: 192080 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1077. Min Act: -0.1700
Data Index: 138225 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1390. Min Act: -0.1700
Data Index: 3094606 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1077. Min Act: -0.1700
Data Index: 8072304 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0765. Min Act: -0.1700
Data Index: 6755081 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0765. Min Act: -0.1700
Data Index: 986942 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0765. Min Act: -0.1700
Data Index: 1477961 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1077. Min Act: -0.1700
Data Index: 8069285 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0765. Min Act: -0.1700
Data Index: 173015 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0765. Min Act: -0.1700
Data Index: 5453504 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0765. Min Act: -0.1700
Data Index: 8505292 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0452. Min Act: -0.1700
Data Index: 4026248 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0452. Min Act: -0.1700
Data Index: 7741491 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0452. Min Act: -0.1700
Data Index: 7630300 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0452. Min Act: -0.1700
Data Index: 4529066 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0452. Min Act: -0.1700
Data Index: 6521489 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0452. Min Act: -0.1700
Data Index: 4627723 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19