Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0087. Min Range: -4.0087
Max Act: 4.0087. Min Act: -0.1700
Data Index: 7003697 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.9149. Min Act: -0.1700
Data Index: 5405344 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.8837. Min Act: -0.1700
Data Index: 8020967 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.8524. Min Act: -0.1700
Data Index: 1117577 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.8524. Min Act: -0.1700
Data Index: 1801078 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.8211. Min Act: -0.1700
Data Index: 5604999 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.8211. Min Act: -0.1700
Data Index: 8606744 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7898. Min Act: -0.1700
Data Index: 2670919 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7898. Min Act: -0.1700
Data Index: 4785468 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7898. Min Act: -0.1700
Data Index: 2641754 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7898. Min Act: -0.1700
Data Index: 2852984 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7586. Min Act: -0.1700
Data Index: 2641747 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7586. Min Act: -0.1700
Data Index: 4547595 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7586. Min Act: -0.1700
Data Index: 5455278 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7586. Min Act: -0.1700
Data Index: 2437749 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7586. Min Act: -0.1700
Data Index: 815177 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7586. Min Act: -0.1700
Data Index: 6498956 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7586. Min Act: -0.1700
Data Index: 4798988 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7586. Min Act: -0.1700
Data Index: 5604998 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0087. Min Range: -4.0087
Max Act: 3.7273. Min Act: -0.1700
Data Index: 2934092 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19