Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6325 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6865. Min Range: -7.6865
Max Act: 7.6865. Min Act: -0.1700
Data Index: 5080258 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.9990. Min Act: -0.1700
Data Index: 8357804 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.9678. Min Act: -0.1700
Data Index: 5554305 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.9678. Min Act: -0.1700
Data Index: 4115950 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.9678. Min Act: -0.1700
Data Index: 856799 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.9053. Min Act: -0.1700
Data Index: 4242817 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.8740. Min Act: -0.1700
Data Index: 344223 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.8428. Min Act: -0.1700
Data Index: 3906469 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.8740. Min Act: -0.1700
Data Index: 3811301 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.8740. Min Act: -0.1700
Data Index: 1608174 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.8115. Min Act: -0.1700
Data Index: 2141667 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.7803. Min Act: -0.1700
Data Index: 6231322 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.7490. Min Act: -0.1700
Data Index: 436520 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.7490. Min Act: -0.1700
Data Index: 1843356 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.7178. Min Act: -0.1700
Data Index: 1242395 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.7178. Min Act: -0.1700
Data Index: 4493005 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.7178. Min Act: -0.1700
Data Index: 489044 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.6865. Min Act: -0.1700
Data Index: 7062230 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.6865. Min Act: -0.1700
Data Index: 6728001 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6865. Min Range: -7.6865
Max Act: 6.6865. Min Act: -0.1700
Data Index: 1632007 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19