Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2415 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0774. Min Range: -8.0774
Max Act: 8.0774. Min Act: -0.1700
Data Index: 4221184 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0774. Min Range: -8.0774
Max Act: 8.0774. Min Act: -0.1700
Data Index: 4787063 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.8274. Min Act: -0.1700
Data Index: 5951588 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.8899. Min Act: -0.1700
Data Index: 8075383 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.8274. Min Act: -0.1700
Data Index: 3438319 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.7649. Min Act: -0.1700
Data Index: 7428407 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.7024. Min Act: -0.1700
Data Index: 2693525 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.7024. Min Act: -0.1700
Data Index: 650523 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.7024. Min Act: -0.1700
Data Index: 6815873 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.6399. Min Act: -0.1700
Data Index: 1535688 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.6399. Min Act: -0.1700
Data Index: 3060484 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.6399. Min Act: -0.1700
Data Index: 398381 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.6399. Min Act: -0.1700
Data Index: 6573679 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.5774. Min Act: -0.1700
Data Index: 7111314 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.5774. Min Act: -0.1700
Data Index: 5695768 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.5462. Min Act: -0.1700
Data Index: 249997 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.5149. Min Act: -0.1700
Data Index: 5951596 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.4837. Min Act: -0.1700
Data Index: 4686911 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.4837. Min Act: -0.1700
Data Index: 7658534 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0774. Min Range: -8.0774
Max Act: 7.4524. Min Act: -0.1700
Data Index: 35344 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19