Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5966 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.4775. Min Act: -0.1700
Data Index: 2043830 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.3525. Min Act: -0.1700
Data Index: 6079029 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.3525. Min Act: -0.1700
Data Index: 2823862 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.3213. Min Act: -0.1700
Data Index: 4183862 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.2900. Min Act: -0.1700
Data Index: 4177563 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.2588. Min Act: -0.1700
Data Index: 1006715 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.1650. Min Act: -0.1700
Data Index: 6811122 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.1650. Min Act: -0.1700
Data Index: 6944124 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.1338. Min Act: -0.1700
Data Index: 6842599 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.1338. Min Act: -0.1700
Data Index: 288897 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.1025. Min Act: -0.1700
Data Index: 1295506 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.0713. Min Act: -0.1700
Data Index: 1731268 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.0713. Min Act: -0.1700
Data Index: 6371269 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.0400. Min Act: -0.1700
Data Index: 179144 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.0400. Min Act: -0.1700
Data Index: 6897153 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.0400. Min Act: -0.1700
Data Index: 6670700 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.0400. Min Act: -0.1700
Data Index: 6491646 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.0400. Min Act: -0.1700
Data Index: 2997121 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.0088. Min Act: -0.1700
Data Index: 341351 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4775. Min Range: -5.4775
Max Act: 5.0088. Min Act: -0.1700
Data Index: 4832182 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19