Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4978 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.6748. Min Act: -0.1700
Data Index: 8217379 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.4560. Min Act: -0.1700
Data Index: 1331179 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.4248. Min Act: -0.1700
Data Index: 7745926 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.3935. Min Act: -0.1700
Data Index: 1573208 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.3310. Min Act: -0.1700
Data Index: 2134729 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.2998. Min Act: -0.1700
Data Index: 6119480 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.2998. Min Act: -0.1700
Data Index: 7261376 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.2685. Min Act: -0.1700
Data Index: 5358534 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.2685. Min Act: -0.1700
Data Index: 6351164 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.2685. Min Act: -0.1700
Data Index: 1275226 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.2685. Min Act: -0.1700
Data Index: 5656573 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.2060. Min Act: -0.1700
Data Index: 6606505 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.2060. Min Act: -0.1700
Data Index: 7303029 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.1748. Min Act: -0.1700
Data Index: 8823356 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.1748. Min Act: -0.1700
Data Index: 5299919 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.2060. Min Act: -0.1700
Data Index: 4249544 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.1435. Min Act: -0.1700
Data Index: 4978210 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.1435. Min Act: -0.1700
Data Index: 1998152 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.1435. Min Act: -0.1700
Data Index: 493254 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6748. Min Range: -5.6748
Max Act: 5.1748. Min Act: -0.1700
Data Index: 1690526 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19