Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5078 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2891. Min Range: -6.2891
Max Act: 6.2891. Min Act: -0.1700
Data Index: 1795457 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2891. Min Range: -6.2891
Max Act: 6.2266. Min Act: -0.1700
Data Index: 4799578 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.9141. Min Act: -0.1700
Data Index: 3093022 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.8828. Min Act: -0.1700
Data Index: 1651090 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.8516. Min Act: -0.1700
Data Index: 5403408 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.8516. Min Act: -0.1700
Data Index: 1814265 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.8516. Min Act: -0.1700
Data Index: 6338078 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7891. Min Act: -0.1700
Data Index: 2087443 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.8203. Min Act: -0.1700
Data Index: 6659071 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7891. Min Act: -0.1700
Data Index: 2385279 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7578. Min Act: -0.1700
Data Index: 7463880 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7578. Min Act: -0.1700
Data Index: 1789134 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7578. Min Act: -0.1700
Data Index: 3949191 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7578. Min Act: -0.1700
Data Index: 7073923 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7578. Min Act: -0.1700
Data Index: 2074255 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7578. Min Act: -0.1700
Data Index: 6594018 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7578. Min Act: -0.1700
Data Index: 158453 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7578. Min Act: -0.1700
Data Index: 7967888 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7578. Min Act: -0.1700
Data Index: 3945984 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2891. Min Range: -6.2891
Max Act: 5.7266. Min Act: -0.1700
Data Index: 7409899 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19