Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 360 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0936. Min Range: -6.0936
Max Act: 6.0936. Min Act: -0.1700
Data Index: 618232 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0936. Min Range: -6.0936
Max Act: 6.0311. Min Act: -0.1700
Data Index: 5416350 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.9686. Min Act: -0.1700
Data Index: 8392894 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.9374. Min Act: -0.1700
Data Index: 3086161 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.9374. Min Act: -0.1700
Data Index: 4337698 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8436. Min Act: -0.1700
Data Index: 2424297 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8436. Min Act: -0.1700
Data Index: 7911870 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8436. Min Act: -0.1700
Data Index: 4749154 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8436. Min Act: -0.1700
Data Index: 1889226 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8436. Min Act: -0.1700
Data Index: 3012710 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8124. Min Act: -0.1700
Data Index: 7600046 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8124. Min Act: -0.1700
Data Index: 876634 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8124. Min Act: -0.1700
Data Index: 2307994 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8124. Min Act: -0.1700
Data Index: 1200102 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8124. Min Act: -0.1700
Data Index: 2982671 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.8124. Min Act: -0.1700
Data Index: 139567 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.7811. Min Act: -0.1700
Data Index: 3741203 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.7499. Min Act: -0.1700
Data Index: 3976571 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.7811. Min Act: -0.1700
Data Index: 433362 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0936. Min Range: -6.0936
Max Act: 5.7811. Min Act: -0.1700
Data Index: 3262252 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19