Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 508 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2785. Min Range: -6.2785
Max Act: 6.2785. Min Act: -0.1700
Data Index: 2832527 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2785. Min Range: -6.2785
Max Act: 6.1847. Min Act: -0.1700
Data Index: 5944305 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2785. Min Range: -6.2785
Max Act: 6.1535. Min Act: -0.1700
Data Index: 2954372 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2785. Min Range: -6.2785
Max Act: 6.1222. Min Act: -0.1700
Data Index: 367774 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2785. Min Range: -6.2785
Max Act: 6.0910. Min Act: -0.1700
Data Index: 826201 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2785. Min Range: -6.2785
Max Act: 6.0910. Min Act: -0.1700
Data Index: 3923909 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2785. Min Range: -6.2785
Max Act: 6.0285. Min Act: -0.1700
Data Index: 1318473 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.9972. Min Act: -0.1700
Data Index: 1325360 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2785. Min Range: -6.2785
Max Act: 6.0285. Min Act: -0.1700
Data Index: 205530 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.9347. Min Act: -0.1700
Data Index: 4714516 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.9347. Min Act: -0.1700
Data Index: 2102492 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.8722. Min Act: -0.1700
Data Index: 6035891 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.8722. Min Act: -0.1700
Data Index: 5301430 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.8410. Min Act: -0.1700
Data Index: 6421421 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.7472. Min Act: -0.1700
Data Index: 6362733 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.6847. Min Act: -0.1700
Data Index: 3083700 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.6847. Min Act: -0.1700
Data Index: 1215745 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.5910. Min Act: -0.1700
Data Index: 965922 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.5597. Min Act: -0.1700
Data Index: 8051078 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2785. Min Range: -6.2785
Max Act: 5.5597. Min Act: -0.1700
Data Index: 1542458 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19