Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.7781. Min Act: -0.1686
Data Index: 6731804 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.6743. Min Act: -0.1700
Data Index: 3386234 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.4996. Min Act: -0.1700
Data Index: 7281442 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.4820. Min Act: -0.1700
Data Index: 7454166 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.4644. Min Act: -0.1700
Data Index: 7658652 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.4644. Min Act: -0.1700
Data Index: 2130428 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.4292. Min Act: -0.1700
Data Index: 1606386 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.4468. Min Act: -0.1699
Data Index: 2582211 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.4468. Min Act: -0.1699
Data Index: 7075968 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3940. Min Act: -0.1700
Data Index: 5018542 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3940. Min Act: -0.1700
Data Index: 3623184 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3764. Min Act: -0.1700
Data Index: 4677872 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3587. Min Act: -0.1700
Data Index: 8051072 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3587. Min Act: -0.1700
Data Index: 8473123 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3587. Min Act: -0.1700
Data Index: 8551487 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3411. Min Act: -0.1700
Data Index: 5996590 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3587. Min Act: -0.1700
Data Index: 296329 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3411. Min Act: -0.1700
Data Index: 7317802 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3235. Min Act: -0.1700
Data Index: 5090631 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7781. Min Range: -1.7781
Max Act: 1.3235. Min Act: -0.1700
Data Index: 3247805 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19