Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4517 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.7944. Min Act: -0.1700
Data Index: 6064942 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.5756. Min Act: -0.1700
Data Index: 3155138 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.4194. Min Act: -0.1700
Data Index: 2407077 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.3569. Min Act: -0.1700
Data Index: 5432605 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.4194. Min Act: -0.1700
Data Index: 1924515 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.3569. Min Act: -0.1700
Data Index: 858975 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.3569. Min Act: -0.1700
Data Index: 3449294 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.3256. Min Act: -0.1700
Data Index: 1890827 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.2631. Min Act: -0.1700
Data Index: 2816087 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.2319. Min Act: -0.1700
Data Index: 2249398 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.2006. Min Act: -0.1699
Data Index: 7359002 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.1694. Min Act: -0.1698
Data Index: 8756032 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.1381. Min Act: -0.1700
Data Index: 7078860 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.0756. Min Act: -0.1700
Data Index: 7140210 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.0756. Min Act: -0.1700
Data Index: 173764 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.0444. Min Act: -0.1700
Data Index: 6602184 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.0444. Min Act: -0.1700
Data Index: 1595977 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7944. Min Range: -5.7944
Max Act: 5.0444. Min Act: -0.1700
Data Index: 1890814 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7944. Min Range: -5.7944
Max Act: 4.9819. Min Act: -0.1700
Data Index: 5904781 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7944. Min Range: -5.7944
Max Act: 4.9819. Min Act: -0.1700
Data Index: 8222823 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19