Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0138. Min Range: -10.0138
Max Act: 10.0138. Min Act: -0.1700
Data Index: 8054992 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.7638. Min Act: -0.1700
Data Index: 2923007 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.7638. Min Act: -0.1700
Data Index: 604210 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.7638. Min Act: -0.1700
Data Index: 2754062 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.7638. Min Act: -0.1700
Data Index: 1967775 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.7013. Min Act: -0.1700
Data Index: 2329647 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.7013. Min Act: -0.1700
Data Index: 1539955 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.7013. Min Act: -0.1700
Data Index: 6730609 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.6388. Min Act: -0.1700
Data Index: 5534276 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.6388. Min Act: -0.1700
Data Index: 3921149 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.6388. Min Act: -0.1700
Data Index: 8163733 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.6388. Min Act: -0.1700
Data Index: 1621783 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.6388. Min Act: -0.1700
Data Index: 4941930 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.5138. Min Act: -0.1700
Data Index: 4338462 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.5138. Min Act: -0.1700
Data Index: 4318971 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.5138. Min Act: -0.1700
Data Index: 4318972 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.5138. Min Act: -0.1700
Data Index: 6947889 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.4513. Min Act: -0.1700
Data Index: 5848253 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.5138. Min Act: -0.1700
Data Index: 8309489 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0138. Min Range: -10.0138
Max Act: 9.3888. Min Act: -0.1700
Data Index: 5048077 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19