Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4639 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2265. Min Range: -8.2265
Max Act: 8.2265. Min Act: -0.1700
Data Index: 2616293 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.4765. Min Act: -0.1700
Data Index: 2141618 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.4452. Min Act: -0.1700
Data Index: 84262 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.3827. Min Act: -0.1700
Data Index: 7448018 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.3827. Min Act: -0.1700
Data Index: 7890351 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.2890. Min Act: -0.1700
Data Index: 7918901 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.2890. Min Act: -0.1700
Data Index: 6908636 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1640. Min Act: -0.1700
Data Index: 6335959 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1952. Min Act: -0.1700
Data Index: 7825236 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1640. Min Act: -0.1700
Data Index: 6326462 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1640. Min Act: -0.1700
Data Index: 3566729 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1952. Min Act: -0.1700
Data Index: 7918902 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1327. Min Act: -0.1700
Data Index: 7423704 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1327. Min Act: -0.1700
Data Index: 3829466 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1015. Min Act: -0.1700
Data Index: 4572850 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1015. Min Act: -0.1700
Data Index: 4231538 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1640. Min Act: -0.1700
Data Index: 7918900 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1327. Min Act: -0.1700
Data Index: 8485839 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1327. Min Act: -0.1700
Data Index: 6344098 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.1327. Min Act: -0.1700
Data Index: 3110954 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19