Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5610 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0581. Min Range: -8.0581
Max Act: 8.0581. Min Act: -0.1700
Data Index: 275034 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.9331. Min Act: -0.1700
Data Index: 3487176 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.8706. Min Act: -0.1700
Data Index: 4963135 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.8081. Min Act: -0.1700
Data Index: 7527153 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.8706. Min Act: -0.1700
Data Index: 2190540 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.6831. Min Act: -0.1700
Data Index: 7630732 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.6831. Min Act: -0.1700
Data Index: 4548785 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.5894. Min Act: -0.1700
Data Index: 5132227 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.4956. Min Act: -0.1700
Data Index: 8390622 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.4956. Min Act: -0.1700
Data Index: 8773930 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.5269. Min Act: -0.1700
Data Index: 8821698 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.5269. Min Act: -0.1700
Data Index: 3384083 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.5269. Min Act: -0.1700
Data Index: 2299886 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.4644. Min Act: -0.1700
Data Index: 682051 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.4644. Min Act: -0.1700
Data Index: 7901902 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.4644. Min Act: -0.1700
Data Index: 2161987 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.4331. Min Act: -0.1700
Data Index: 6178515 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.4331. Min Act: -0.1700
Data Index: 4894199 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.4331. Min Act: -0.1700
Data Index: 3146546 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0581. Min Range: -8.0581
Max Act: 7.4019. Min Act: -0.1700
Data Index: 2653358 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19