Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.8836. Min Act: -0.1700
Data Index: 5745385 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.8523. Min Act: -0.1700
Data Index: 2755576 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.8211. Min Act: -0.1700
Data Index: 4599068 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.7898. Min Act: -0.1700
Data Index: 7240475 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.8211. Min Act: -0.1700
Data Index: 4933815 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.7586. Min Act: -0.1700
Data Index: 6042391 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.7273. Min Act: -0.1700
Data Index: 8008888 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.7586. Min Act: -0.1700
Data Index: 2004298 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.7586. Min Act: -0.1700
Data Index: 7545491 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.7273. Min Act: -0.1700
Data Index: 6882934 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.7273. Min Act: -0.1700
Data Index: 6859127 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.7273. Min Act: -0.1700
Data Index: 2174821 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.7273. Min Act: -0.1700
Data Index: 6704233 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.6961. Min Act: -0.1700
Data Index: 960881 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.6961. Min Act: -0.1700
Data Index: 5049007 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.6961. Min Act: -0.1700
Data Index: 8244972 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.6961. Min Act: -0.1700
Data Index: 654456 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.6648. Min Act: -0.1700
Data Index: 5877582 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.6648. Min Act: -0.1700
Data Index: 4421523 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8836. Min Range: -5.8836
Max Act: 5.6961. Min Act: -0.1700
Data Index: 2344864 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19