Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3821 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0712. Min Range: -7.0712
Max Act: 7.0712. Min Act: -0.1700
Data Index: 1527919 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0712. Min Range: -7.0712
Max Act: 7.0400. Min Act: -0.1700
Data Index: 7395162 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0712. Min Range: -7.0712
Max Act: 7.0087. Min Act: -0.1700
Data Index: 133540 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.7900. Min Act: -0.1700
Data Index: 6776896 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.7900. Min Act: -0.1700
Data Index: 4840165 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.7275. Min Act: -0.1700
Data Index: 725337 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.7275. Min Act: -0.1700
Data Index: 2042466 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.7275. Min Act: -0.1700
Data Index: 120094 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.7275. Min Act: -0.1700
Data Index: 695070 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.6337. Min Act: -0.1700
Data Index: 5142668 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.6650. Min Act: -0.1700
Data Index: 6428213 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.6025. Min Act: -0.1700
Data Index: 3737026 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.6025. Min Act: -0.1700
Data Index: 2323723 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.5712. Min Act: -0.1700
Data Index: 6216785 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.5400. Min Act: -0.1700
Data Index: 5322092 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.5087. Min Act: -0.1700
Data Index: 6094458 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.4775. Min Act: -0.1700
Data Index: 422758 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.4775. Min Act: -0.1700
Data Index: 4573946 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.4462. Min Act: -0.1700
Data Index: 3143315 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0712. Min Range: -7.0712
Max Act: 6.4775. Min Act: -0.1700
Data Index: 6830869 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19