Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1925 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.5006. Min Act: -0.1700
Data Index: 1924591 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.5006. Min Act: -0.1700
Data Index: 3819936 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.4381. Min Act: -0.1700
Data Index: 1385679 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.4068. Min Act: -0.1700
Data Index: 298880 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.3756. Min Act: -0.1700
Data Index: 7301387 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.2818. Min Act: -0.1700
Data Index: 1780453 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.2506. Min Act: -0.1700
Data Index: 4842162 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.2818. Min Act: -0.1700
Data Index: 7249117 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.2193. Min Act: -0.1700
Data Index: 8783359 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.2193. Min Act: -0.1700
Data Index: 894371 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.2193. Min Act: -0.1700
Data Index: 5855496 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.2506. Min Act: -0.1700
Data Index: 6314110 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.1568. Min Act: -0.1700
Data Index: 6160481 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.1881. Min Act: -0.1700
Data Index: 406221 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.1881. Min Act: -0.1700
Data Index: 5716790 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.1881. Min Act: -0.1700
Data Index: 4411237 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.1881. Min Act: -0.1700
Data Index: 475134 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.1881. Min Act: -0.1700
Data Index: 4887125 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.1256. Min Act: -0.1700
Data Index: 76676 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5006. Min Range: -5.5006
Max Act: 5.1568. Min Act: -0.1700
Data Index: 2986282 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19