Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5770 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.6072. Min Act: -0.1700
Data Index: 8788 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.3260. Min Act: -0.1700
Data Index: 4016299 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.2947. Min Act: -0.1700
Data Index: 7446146 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.2322. Min Act: -0.1700
Data Index: 3267112 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.2010. Min Act: -0.1700
Data Index: 8508964 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.1697. Min Act: -0.1700
Data Index: 4227981 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.1385. Min Act: -0.1700
Data Index: 2216514 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.0760. Min Act: -0.1700
Data Index: 3286358 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.0760. Min Act: -0.1700
Data Index: 6960268 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.0760. Min Act: -0.1700
Data Index: 8189477 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.0760. Min Act: -0.1700
Data Index: 4098249 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.0447. Min Act: -0.1700
Data Index: 227096 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6072. Min Range: -5.6072
Max Act: 5.0447. Min Act: -0.1700
Data Index: 3972174 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6072. Min Range: -5.6072
Max Act: 4.9822. Min Act: -0.1700
Data Index: 3686001 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6072. Min Range: -5.6072
Max Act: 4.9822. Min Act: -0.1700
Data Index: 6212080 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6072. Min Range: -5.6072
Max Act: 4.9822. Min Act: -0.1700
Data Index: 5660628 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6072. Min Range: -5.6072
Max Act: 4.9822. Min Act: -0.1700
Data Index: 7026812 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6072. Min Range: -5.6072
Max Act: 4.9822. Min Act: -0.1700
Data Index: 1305095 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6072. Min Range: -5.6072
Max Act: 4.9510. Min Act: -0.1700
Data Index: 2938935 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6072. Min Range: -5.6072
Max Act: 4.9510. Min Act: -0.1700
Data Index: 2944370 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19