Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1754 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0213. Min Range: -5.0213
Max Act: 5.0213. Min Act: -0.1700
Data Index: 8330955 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.8651. Min Act: -0.1700
Data Index: 4251531 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.6776. Min Act: -0.1700
Data Index: 276091 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.6776. Min Act: -0.1700
Data Index: 6480854 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.6463. Min Act: -0.1700
Data Index: 4400228 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.6776. Min Act: -0.1700
Data Index: 4251530 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.6463. Min Act: -0.1700
Data Index: 8141423 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.6151. Min Act: -0.1700
Data Index: 8505621 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.5838. Min Act: -0.1700
Data Index: 1206800 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.5838. Min Act: -0.1700
Data Index: 6582129 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.6151. Min Act: -0.1700
Data Index: 7329066 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.5213. Min Act: -0.1700
Data Index: 7054699 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.5526. Min Act: -0.1700
Data Index: 3602172 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.4901. Min Act: -0.1700
Data Index: 1683798 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.4588. Min Act: -0.1700
Data Index: 6069232 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.4901. Min Act: -0.1700
Data Index: 2568003 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.4901. Min Act: -0.1700
Data Index: 4245961 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.4901. Min Act: -0.1700
Data Index: 1815959 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.4588. Min Act: -0.1700
Data Index: 8085804 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0213. Min Range: -5.0213
Max Act: 4.4588. Min Act: -0.1700
Data Index: 5601718 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19